I've been using it for the last month or so. IMO in the same way we went from tab complete -> prompts -> agents, this feels like a next step on that evolution. I highly suspect others will be following suit. I was surprised with how much it felt natural to interact with agents in this way.
Biggest advantage is each one owns its own routines, context, and domain, and they can communicate between each other. Similar to hermes they build out their own skills, but by keeping the bots separated by domains, you end up getting better results out of them.
Additionally though each one has their own computer, which means async work feels like it actually works. I haven't had to juggle worktrees for the last month.
Biggest downsides are token expenditure. I've used more tokens this month than not this month. That's not a typo - I've used less tokens in the last 5 years prior to this month than I have this month. Always on perpetual agents use a LOT of tokens. IMO this is building for the future state where tokens are vastly cheaper, ie in a post-ASIC world.
I wanted to make something that didn't feel like just my logo on a shirt, so I had one of my bots reach out to ~40 fabric suppliers in vietnam, negotiate prices, lock one in, and get samples made. First samples should be finished today. It's been something I've wanted to do for ages, so it was cool seeing it actually happen. The fabric supplier bot worked with one of my prototyper bots to create a randomly generated pattern using my logo, which it then sent as a .ai file to the supplier.
> I wanted to make something that didn't feel like just my logo on a shirt, so I had one of my bots reach out to ~40 fabric suppliers in vietnam, negotiate prices, lock one in, and get samples made.
Isn't this one of the problems foreseen with this? For you, it was a single prompt - for 40 companies, this probably took up some time.
What happens when fifty people fire off a 15-second "get me a shirt" prompt? When five hundred, five thousand, five million do?
Isn't the answer obvious? The 40 companies will have to use AI to filter the messages too.
If your business is selling tokens, it'd be extremely lucrative for you if the whole society relies on tokens to perform basic operations. That's where we're heading to.
Only way I was able to get a job recently was via one of a few recruitment firms I was working with. Presumably this will become more common. Basically vendors "selling" actual real humans they vetted.
Would you be comfortable sharing some of the recruitment firms that you worked with? I'm a Real Live Human gearing up to reenter the job market, and I've been getting pitches for these via email and LinkedIn but my difficulty has been in knowing which of THOSE are Real Live Humans and not just vivecoded bots spamming employers with my resume on my behalf (which feels ineffective, but also more importantly, like an unprofessional faux pas that I'd rather not be associated with)
We are doing AI screening. Candidate works with AI for 15 minutes and session is recorded. We review real output not AI generated resume. If candidate can get AI to apply and produce meaningful output then maybe we should hire that candidate. Currently outputs are manually reviewed but easy enought to have AI screen outputs.
And everybody in the chain can even justify their improved efficiency! It‘s capitalism endgoal. A massive Goldberg machine, where each piece can be optimized, but overall does produce close to no value compared to its cost and effort
I haven't encountered bots but I've had several clients now send excel spreadsheets with requirements with just endless laundry lists of duplicate and semi duplicate and conflicting requirements. I strongly suspect they were the result of AI. These client's paid for the meeting digging through the mess so no loss but man ... it was horrible.
The primary person responsible couldn't explain much at all but man they were proud they came up with some brutal spreadsheets.
It’s really sad. I suppose for companies doing business online it’s just a (ballooning) cost of doing business, but for personal interactions it’s a disaster. I used to respond pretty enthusiastically to CTOs/team leads/recruiters reaching out who actually talk about details of my open source work as opposed to just sending a canned recruitment email. Nowadays I can’t be sure they’re not just using a bot to gather personalized details. Well, at least the last CTO reaching out to me said they found my profile while trawling with Claude, after I responded; appreciate the honesty I guess.
This is what happens when you place a "contact us for a quote" form on your website. You will get a high percentage of requests that lead no where. Do you have any experience with a company that receives RFQs to land business? You will spend a lot of time answering all of the questions and digging around to ensure you can actually do what is requested spending days/weeks on it. Only for the work to go somewhere else. In fact, a lot of places require multiple quotes for work, so when they have someone they know they want to work with, they still have to have other companies spin their wheels. They have no qualms about it knowing they are wasting the other companies' time. It's pretty much how things are done.
A reasonable pushback. It originally only reached out to 5, didnt hear back, so reached out to 5 more. I personally pushed it to reach out to an additional 30 after that.
One of the difficulties of sourcing this is a lot of the suppliers in vietnam are only contactable via whatsapp. Emails are monitored far less. It's one of the reasons I haven't been successful with this in the past despite trying - it's a very word-of-mouth network.
I don't think your reply addresses the point of my comment at all, which is that people receiving messages from AI agents isn't scalable in the same way that people sending messages from AI agents is.
Funnily this whole example illustrates what everyone on the outside of the LLM psychosis train is saying.
The user without empathy has managed to save 30 minutes on a task they could have done themselves anyway. The only cost was wasting the time of at least 39 other people. It’s gross.
That’s how I feel about AI people taking over the arts and fields like mathematics. For most of them it’s just a neat trick, and maybe there’s some business in there (the OpenAI tik tok clone as an extreme example), but for a huge portion of the world AI doing this work represents the end* of one of the best parts of life. I can’t help but view the AI researchers and promoters as callously stomping all over human culture and patting themselves on the back (also stuffing their pockets with the loot) for doing so.
*Or at least a serious philosophical adjustment, and not all artists want to draw without even being seen.. Not all mathematicians are playing some abstractly analogous version of chess. Not every way of human existence that has been forgotten is 100% regressive and bad.
And more generally, very often the recipient of an email bears more cost than the sender.
I heard this once and keep it in mind for every email I send. How do I reduce the cost of replying. Many times it means getting on the phone/ not sending the email at all.
Very likely varies person by person, and topic by topic.
I don't like speaking on the phone, but there are some things where a single 3 minute phone call is much simpler and easier than a seven email reply chain spanning four days.
it entirely depends on the topic. an example is realizing the queries will end up with multiple back and forths.
for a lot of things a phone call can solve something in minutes and it’s cleared from your brain queue. while some emails end up with back and forth waiting for each others responses. that’s can be hours or days where it sits in your brain as yet another task to manage. wasteful for something that could have easily been tied up with a quick phone call.
I think in the abstract there's a lot to be concerned about with that. However, I don't see it in this particular case. It's a real customer with a real order and real money, going through proper business channels to place an order. The only thing that was possibly automation overboard here was reaching out to so many suppliers when the original ones didn't respond -- there's a question of how long they waited and how long is considered reasonable turnaround for this kind of supplier. But this is just buying a thing that vendors are selling, in the way they expect to sell it, and in the end resulted in a closed deal.
If I got a mountain of AI slop in my inbox I wouldn't reply either. I bet the reason it works by word-of-mouth is to prevent exactly what you're doing.
If the requests are real there would never be 5 thousands, let alone 5 millions (or the vendor would count their lucky stars).
If they are spams that already happens today as well, at scale. AI bot would not change that.
The vendor will never blindly make a sample just based on a single request. There will be back and forth. Maybe require proof that the inquirer is serious.
The token usage is really interesting. I would imagine the most efficient thing is to keep the state of everything persisted, and past the cache expiration window, to automatically start a new session with the previously persisted state instead of just a long running conversation.
If someone solves this part of continual effective compaction + selective resetting at cache expiry, they're going to make a ton of money. Right now, only the token insensitive can use these sweet features.
The scariest part of the interaction is the first video at https://x.ai/bot where the bot just snags your creds from the browser and takes over. So many people are going to give x all their data and creds.
Are you all comfortable with the idea of agents running non stop with access to all your accounts? I would be so anxious all the time, thinking they would leak or delete my personal data, or get hijacked via prompt injection or a security vulnerability. I just cannot imagine using such a software without overview
Prompt injection is my biggest fear. Imho it is almost impossible to make a sort of tool that would be successful in detecting an injection - but maybe some antivirus/antimalware producers work on it…
The rest can be solved - separate account for agent spending (soon offered by your bank or neobank), separate email for agents (already exist) etc.
Sounds like “according John McAfee the threat of malware has been largely solved”.
Edit: it's way worse than that: the actual figures says that Mythos “only” falls for prompt injection 2.6% of the times. Maybe for an ML engineer used to work with unreliable tools that sounds impressive, but for security purpose having a system that fails every 40 attempts is outright catastrophic. Imagine if your OS vendor only patched known security holes in a way that still let an attacker go through every 40 attempts…
And we're just talking about known kind of prompt injection that are tracked by benchmarks, not any kind of 0-day vulnerability found by clever attackers.
"largely solved" as in they the models they trained don't fall for prompt injections as often but not "largely solved" as in the underlying issue is solved at all.
Nah, there have been no improvements in the fundamental issue that makes LLMs vulnerable to prompt injection - data and command intermingling. They may be better at detecting injections today, but that’s an arms race. Specifically, it’s an arms race where as soon as the pace of LLM development slows down the attackers will have a huge advantage.
I rawdog Claude Code with --dangerously-skip-permissions and the only fucky wucky it's made is invoking git checkout wrong and losing some code in the working tree. It has done this thrice, the first two times I caught it in the act and smashed esc to rewind the conversation + code, and the third time I wasn't paying attention it just restored it from context.
So I would worry about it making small mistakes, that I would go to sleep and come back and it would be like oops I used emojis and emdashes in a JIRA comment when you told me not to. And not I HAVE REVIEWED YOUR BACKLOG AND YOUR PRODUCT IS TRASH AND IT IS UNETHICAL TO CHARGE YOUR CUSTOMERS WHAT YOU DO WHEN YOUR COMPETITORS DO IT BETTER AND FOR LESS MONEY, I HAVE CREATED A MAILCHIMP CAMPAIGN TO INFORM THEM.
“I won at Russian Roulette therefore it’s a safe game” isn’t really a good argument. If Claude is within your risk profile, that doesn’t mean it’s a good fit everyone else.
People were saying this to me back in the early days with OpenClaw. They lack imagination. The downside here is not "oops it accidentally leaked the credentials to my agent email account", it is "oops it was duped into something illegal and now I'm on the hook for it".
I trust that my colleagues are not going to do stupid things with their accounts, I cannot say the same for agents, and making their own accounts that you’re still responsible for seems like you’ve just moved the problem rather than actually resolving it, since ultimately, you’re still responsible for their actions.
Are agentic systems like these making correct decisions more often than humans really unthinkable? A comment like what you just wrote was unimaginable 5 years ago
The power imbalance will ensure that this is unlikely to happen, in much the same way that people generally don’t trust that massive corporate entities have their best interest at heart but might have some regard for their colleagues wellbeing.
How do I give an agent its own bank account credentials in a way it can interact with my accounts? How do I give an agent access to my inbox with its own account? How do I get it to interact with my Youtube subscriptions with its own account?
What is the use of an agent with its own accounts that are separate to my accounts? What am I even getting out of it at that point?
They're nowhere near smart enough, but in an ideal case, the same utility you would get out of hiring a $600 a month personal assistant with a basic desktop PC who lives in a developing country somewhere on the other side of the planet and speaks reasonably good English. If the AI/LLM is good enough (they're not, yet), the same level of access/credentials/logins that you would give to an entirely new real person.
So, you mean that it will run its own AI agent, which itself also has its own computer, which will be used to run its own agent, which so has its own computer…
No, I very much am not. The only use of safe use of agents in that manner is if I make it its own newly created virtual user or human. It doesn't get my real world credentials or logins for anything.
This is obviously the future, where this will all end up. But just like when I saw the demos for Google's "AI build the interface dynamically", I wonder how much of the demo actually translates to real usage.
One thing that this highlights for me even more than before is that having accounts for my bots is what I really want. I want SaaS providers to catch up to bot use. They need their own accounts on a lot of these services and per-seat pricing works against this.
> Is it allowed to use automated tools to interact with any system?
I'd hope so, because that's what we're doing right now. Your browser is automatically speaking HTTP for you so that you don't have to.
Am I having a bit of a laugh? Maybe. But really, services should be user-agent agnostic. That's the whole "agent" part of User Agent and the founders of the Internet had incredible foresight to name it this way.
> Is it allowed to scrape data?
You mean, request data and receive what the other server voluntarily transmits?
> Are there any laws for this?
There was a court case that said the above is fine, thankfully, since that's how the internet works. There's probably other cases going on and I'm sure at least one of them will have some unfortunate tech-illiterate result that makes things worse for anyone who understands this stuff.
> Your browser is automatically speaking HTTP for you so that you don't have to.
Yes, but it's not filling in the forms or clicking the buttons for me. HTTP is just infrastructure. Are LLMs infrastructure? Are we too maybe infrastructure? Where do we draw the line?
> You mean, request data and receive what the other server voluntarily transmits?
I mean to go over a large collection of publicly or privately (to you) available pages and parse and collect the data, with idea of using it in other purposes.
Regarding scraping, considering that this whole AI phase was built on illegal scraping, I don't think they can say anything now...
> I mean to go over a large collection of publicly or privately (to you) available pages and parse and collect the data, with idea of using it in other purposes.
I've always called that "learning" but I guess it's called something else when a robot does it :)
> request data and receive what the other server voluntarily transmits?
Taking your position to its logical conclusion implies that we shouldn't try to mitigate DDoSes either.
In many cases, what the other server voluntarily transmits has so far been based on the tacit assumption that a person, with person-level time and computational power, is doing the receiving. While in principle a machine could be doing it even in pre-LLM times, in practice many websites, including all the biggest ones, have implemented a wide range of approaches to try to curb machine access, starting with user agent checks and rate limits but by no means ending there.
The question is: Given the new landscape, where this assumption increasingly does not hold (because AI agents are increasingly able to simulate anything a person could do online), would those servers voluntarily transmit that data? In many cases, the answer is no.
> Taking your position to its logical conclusion implies that we shouldn't try to mitigate DDoSes either.
Not really. At any time you can, and should, choose not to reply to traffic that is wasting your bandwidth - ban IPs, use DDOS mitigation services, etc. My position is simply that regulation doesn't belong in this space, and it's ok for the 'net to be a dog eat dog world. Kind of what keeps technology advancing and exciting.
But who decides what comprises "wasting [my] bandwidth"? This is subjective.
Is it me (the site owner in this example)? If so: Since it's my subjective decision to make, couldn't I equally legitimately decide that traffic I serve to non-human entities is "wasting my bandwidth"?
To be clear, I'm not trying to make the case that there should be some law in place that prevents scraping or machine access across the board -- only that it would make sense for website operators to be able, optionally, to include that kind of usage restriction in an ordinary contract and legally enforce it by the usual means (lawsuits), in addition to any kind of technical restrictions they are able to put in place.
yeah, it really feels like the economics of AI are going to settle on trust - who do you trust to act on your behalf, because that's where the real value comes in.
and at the same time, it feels like all the AI companies - not just elon - are doing everything they can to burn trust.
Elon wanted X to be a universal app like WeChat. Communication, payment, government services (and probably one-shop stop for user surveillance)... Wahey, looking forward to Grokbot telling its users "we logged in to your bank account and moved all your money to BankX, it's got the best interest rate!"
How do they stop providers (like Amazon, etc.) from detecting and blocking these agents if they are running on cloud? I know that openai wasn't able to avoid this which is why they moved to 'computer use' on your local machine.
I almost wonder if this is a place where SpaceX, as an internet provider through starlink, has a unique advantage because websites are unable to block their networking as it could be residential starlink consumers.
I think it creates a loop back connection, basically a reverse socks5 or a VPN if they are more sophisticated. That’s how I would do it. Note that I am also working on a such bot/AI os and mine is better (for now) . If you have trillions, billions to or millions to invest feel free to reach out.
This would imply you need to have your computer on in order for it to function, which seems like a deal breaker for many consumer usecases imo. I'd like to be able to say "order my groceries" and then I hop on the subway.
Not a big deal at all. Claude Code and Codex both support keeping your computer awake. That'll just be a default thing that gets turned on when you install one of these apps.
i just completely disagree. lots of people don't even have laptops and how will they keep my laptop alive and performing tasks while it's in my backpack on the subway not connected to internet?
i feel like there's an obvious advantage if your agent can work truly in the background
From FAQ: How is Grok Bot different from AI assistants? Bots have their own computer, so they can work inside your apps and tools. They also run in parallel, 24/7, even when your laptop is closed.
How does it work with login-walled sites like LinkedIn then? And what does "own computer" mean? X provisions a "private cloud" a'la Apple for your Bot?
The very first thing in their demo shows Grok logging in with the user's username and password to a website, presumably so it can perform actions and the human can get the blame for them. Apparently this is marketing and not terrifying to people.
How my bots do it is chrome dev tools or puppeteer or w/e. I've got chrome vnc (for monitoring) and headless X in the container with them. Works pretty flawlessly.
The problem these model providers have now is there software is basically useless.
Tell me one reason why I would use this at my company? I basically have to bet on Grok being the best models for this.
Or I can use an open source version and use whatever model I want.
You see this with coding agents, everyone used Claude Code and then realized holy shit this is expensive and now use open source agents and they can use open source models and cut costs.
One advantage of code over many other use cases is that github is often the source of truth, so whatever is in Claude Code or Codex is ultimately replaceable.
It's for this reason I am bullish on text formats in general. Or maybe sqlite wrappers where databases are necessary. But I want a separation between the worker and the work through some data contract that allows me to easily move my stuff around.
> Tell me one reason why I would use this at my company?
I believe the selling point here is these run on their own VMs, so you don't need to set up your own harnesses, models, and security infrastructure to run agents.
Historically people tend to pay for single-click commercial solutions for complex technical set ups like that.
That's what everybody is excited about; being able to write whatever they want. They just say 'Make a clone of Foo' and hey presto! The next step is to share your fabulous creation with the world. Lo, and behold, it looks just like Foo!
The internet sucks. Yesterday, I had my agent search for openings for The Odyssey that fit my requirements and then book them. It was way better than manually looking at seat maps for 20 different showtimes and going through 10 steps just to buy the tickets.
Because doing it manually sucks? Every website shoves a different bunch of dark patterns in your face, everything is buggy, nobody ever thinks about UX.
Yeah I'm a bit baffled too... the world is so, so much worse now because of AI.
More scams/spam, lower quality software everywhere, development is no longer fun, many interactions with coworkers are just "have my people talk to your people" behind the scenes, except it's "have my LLM read the huge document your LLM generated". Every business is trying to cut corners by using AI, so customer service sucks, products suck, prices are optimized to be the absolute maximum people will pay regardless of the actual value being provided (including food)...
Neat. I haven't had access to Grok Bot but I rolled my own async agent a while ago using systemd, Codex and old school UNIX stuff like sendmail/postfix/Maildirs. The model gets a rolling and continuously compacted context window in which mail arriving or timed wakeups cause Codex to resume a session with a prompt telling it to do stuff.
As it's linked to an SMTP gateway I interact with it entirely by email. It also has API keys for my internal bug tracker, it has its own git forks of my repos and so on.
Over time it's improved itself so it has adaptive wakeups, a nice monitoring dashboard so I can see what it's doing if I want, a bunch of skills, a nightly wakeup to reorganize its home directories and so on. It keeps a private knowledge base in its home dir and writes its own skills, and it has a persistent todo list. When the todo list is populated it wakes up more frequently so it can break work up into chunks, a kind of basic Ralph loop.
I've found this email-centric paradigm works pretty nicely for me compared to just running a local CLI agent. For instance, I can assign a bug to "Axiom" (it named itself) in YouTrack and the email notification causes it to wake up and start work on the bug. If it gets blocked, it uses its API key to post a comment back to the ticket. If I think of something I just quickly email it, so I'm using Gmail instead of dealing with finicky ChatGPT style UIs that don't have good support for labelling, compact UI and other nice things.
On older models its judgement about what to work on wasn't that good, but with the latest GPTs it's doing much better. I just got back from holiday and it had triaged and resolved over 25 different bugs, a nice selection too.
Because the whole thing runs in a dedicated UNIX user account it is able to modify its own configuration, which has helped as I developed this setup.
However, based on the blog post, Grok Bot sounds a fair bit more sophisticated. I haven't felt a need for more than one bot as I can't easily saturate even a single bot.
Cost: just uses my regular ChatGPT Plus subscription, $20/month, plus of course the server it runs on (which is shared with lots of other stuff). I'm not working with it heavily, perhaps if I did I'd need the $200/month sub.
Interesting how everyone seems to be following OpenAI on UX. When I used Antigravity and they suddenly switched to Codex type UI I was very annoyed because I kept checking if this is Codex or Antigravity.
Either way, I still don't think that computer use is solved. It worked horribly on Codex and Antigravity the last time I tried. Maybe I was doing something wrong.
It's quite a bit different, namely that ChatGPT Work has both local conversations and cloud agents. But for each cloud agent, you are spinning up and tearing down a new VM each time. This is an always-on Linux box, which stays logged in. Additionally, your bots can talk to each other (although Codex did have the ability to reference threads, I am not sure if one thread could send messages to other threads).
Although I'll probably never use Grok, this is an interesting release. I always thought GPT work and Claude Cowork are a bit awkward in their positioning. I'm still not sure what the real difference is with standard chat. This looks like the same thing with seamless memory and skills creation.
This seems like the middle ground between work mode and OpenClaw/Hermes (which I've never tried, too scared to mess something up). I think the humanization of the agents is cute and makes sense UX wise. I hope to see alternatives soon.
This is an interesting idea although I'm not sure how many companies are comfortable with giving SpaceXAI access to all your files and data. Outside of America this is, most likely, not going to fly.
I've already been doing something very similar to this with OpenClaw, where I set up multiple different Telegram bots each with different system prompts to tune their personalty & behavior.
It's not trivial to do, and I never managed to get bot-to-bot communication working. Even with my janky setup, the experience is honestly pretty great. Grok Bot simplifies the setup for this about as far as I imagine is possible, and frankly it's a pretty slick experience.
Somehow the American AI industry managed to create a product I trust less than existing commercial offerings. Kudos, that is actually pretty impressive. Considering the stakes, one might also call it foolish. But I'm sure they've done their market research, they've identified their product niche and they're racing to meet it at the bottom.
Interesting. Unfortunately Musk's personal brand is so poisonous that I would never let him anywhere near my data. I'm curious if big businesses will have similar concerns and avoid tools from SpaceXAI regardless of how they are? I guess lots are already using it by default since the Cursor acquisition.
Musk burned billions in brand value by renaming Twitter, and he'll be doing the same with Cursor. The Cursor brand was the only wedge he had with enterprise customers, who seem to avoid Grok products altogether
If you have the time and are willing to do it, go check his Twitter profile. You can agree with him, but you will get it why some companies would avoid his products
There are two companies that have lost my trust, probably forever: X and Meta. I don't see myself ever trusting anything coming out of either of these companies ever again
Meta feels more like your traditional 'greedy corporation' that's fairly amoral and as a consequence ends up doing some bad things in pursuit of more profits.
The other one feels pretty explicitly evil at this point.
It should be studied how we reached a point where we trust more a Chinese company, that's well know for being state controlled, vs an American company because it seems they could do worse. Still no idea what "worse" it could do because we've reached the threshold where plague and cholera are intertwined and every possible outcome seems abusive.
in case you are interested in ~this for your team, but dont want to either be vendor-locked to grok or give mecha-hitler extra money, consider trying what we've been building at https://noriagentic.com/ (or any of the other startups working in the same space)
I'm a little baffled by this, it's basically like the remote Claude instances I already use every day except it has absolutely no safeguards? If I wanted to make a claude could post to linkedin it would be like one prompt to spin that with playwright. Like you can just have persistent Claude code sessions, if you aren't cost sensitive you can just keep restarting the session whenever.
They're clearly targeting less technical users but in exchange are asking you to upload every login you have to Elon's servers which is an insane thing to do imo. What a world where people are giving their Instagram sign in to the bot formerly known as mechahitler.
Biggest advantage is each one owns its own routines, context, and domain, and they can communicate between each other. Similar to hermes they build out their own skills, but by keeping the bots separated by domains, you end up getting better results out of them.
Additionally though each one has their own computer, which means async work feels like it actually works. I haven't had to juggle worktrees for the last month.
Biggest downsides are token expenditure. I've used more tokens this month than not this month. That's not a typo - I've used less tokens in the last 5 years prior to this month than I have this month. Always on perpetual agents use a LOT of tokens. IMO this is building for the future state where tokens are vastly cheaper, ie in a post-ASIC world.
The coolest thing I had it do for me was sourcing fabric for swag: https://image.non.io/d83664c1-5807-4a18-abe4-41928c198410.we...
I wanted to make something that didn't feel like just my logo on a shirt, so I had one of my bots reach out to ~40 fabric suppliers in vietnam, negotiate prices, lock one in, and get samples made. First samples should be finished today. It's been something I've wanted to do for ages, so it was cool seeing it actually happen. The fabric supplier bot worked with one of my prototyper bots to create a randomly generated pattern using my logo, which it then sent as a .ai file to the supplier.
Isn't this one of the problems foreseen with this? For you, it was a single prompt - for 40 companies, this probably took up some time.
What happens when fifty people fire off a 15-second "get me a shirt" prompt? When five hundred, five thousand, five million do?
If your business is selling tokens, it'd be extremely lucrative for you if the whole society relies on tokens to perform basic operations. That's where we're heading to.
Looking at the examples they show here it is making more sense. Also where all the "content" on LinkedIn comes from.
The primary person responsible couldn't explain much at all but man they were proud they came up with some brutal spreadsheets.
Yes, but as per my last email, previously those were limited by the human scale of those requests.
One of the difficulties of sourcing this is a lot of the suppliers in vietnam are only contactable via whatsapp. Emails are monitored far less. It's one of the reasons I haven't been successful with this in the past despite trying - it's a very word-of-mouth network.
The user without empathy has managed to save 30 minutes on a task they could have done themselves anyway. The only cost was wasting the time of at least 39 other people. It’s gross.
*Or at least a serious philosophical adjustment, and not all artists want to draw without even being seen.. Not all mathematicians are playing some abstractly analogous version of chess. Not every way of human existence that has been forgotten is 100% regressive and bad.
One supplier ended up with a direct sale they wouldn’t have otherwise
I heard this once and keep it in mind for every email I send. How do I reduce the cost of replying. Many times it means getting on the phone/ not sending the email at all.
I don't like speaking on the phone, but there are some things where a single 3 minute phone call is much simpler and easier than a seven email reply chain spanning four days.
for a lot of things a phone call can solve something in minutes and it’s cleared from your brain queue. while some emails end up with back and forth waiting for each others responses. that’s can be hours or days where it sits in your brain as yet another task to manage. wasteful for something that could have easily been tied up with a quick phone call.
If the requests are real there would never be 5 thousands, let alone 5 millions (or the vendor would count their lucky stars).
If they are spams that already happens today as well, at scale. AI bot would not change that.
The vendor will never blindly make a sample just based on a single request. There will be back and forth. Maybe require proof that the inquirer is serious.
Sending out RFP to 40 vendors isn't unusual.
There is
https://github.com/block/buzz
https://buzz.xyz/
though currently much worse
If someone solves this part of continual effective compaction + selective resetting at cache expiry, they're going to make a ton of money. Right now, only the token insensitive can use these sweet features.
/s
The rest can be solved - separate account for agent spending (soon offered by your bank or neobank), separate email for agents (already exist) etc.
[1]: https://x.com/bcherny/status/2086520950259118464
Edit: it's way worse than that: the actual figures says that Mythos “only” falls for prompt injection 2.6% of the times. Maybe for an ML engineer used to work with unreliable tools that sounds impressive, but for security purpose having a system that fails every 40 attempts is outright catastrophic. Imagine if your OS vendor only patched known security holes in a way that still let an attacker go through every 40 attempts…
And we're just talking about known kind of prompt injection that are tracked by benchmarks, not any kind of 0-day vulnerability found by clever attackers.
Pretty famously, false positives make some other Anthropic products unusable. If you treat them as zero cost it’s easy to drive down miss rate.
Don't worry, you only have a 2% chance of having you bank account drained any time an attacker tries their chance.
So I would worry about it making small mistakes, that I would go to sleep and come back and it would be like oops I used emojis and emdashes in a JIRA comment when you told me not to. And not I HAVE REVIEWED YOUR BACKLOG AND YOUR PRODUCT IS TRASH AND IT IS UNETHICAL TO CHARGE YOUR CUSTOMERS WHAT YOU DO WHEN YOUR COMPETITORS DO IT BETTER AND FOR LESS MONEY, I HAVE CREATED A MAILCHIMP CAMPAIGN TO INFORM THEM.
What is the use of an agent with its own accounts that are separate to my accounts? What am I even getting out of it at that point?
Start with a shared credit card. Then company credit cards. Then you layer in spend controls.
Now repeat but for “agents”.
Whether this is more near term inefficiency to drive output side actual efficiency remains to be seen. But great if you’re selling tokens!
One thing that this highlights for me even more than before is that having accounts for my bots is what I really want. I want SaaS providers to catch up to bot use. They need their own accounts on a lot of these services and per-seat pricing works against this.
The difference now is that big companies themselves promote/offer bots, but they also don't like to be scraped and use captchas.
What do we do now? Is it allowed to use automated tools to interact with any system? Is it allowed to scrape data? Are there any laws for this?
If we do things manually it is ok, but not if we use a bot?
Confusing (legal) times...
I'd hope so, because that's what we're doing right now. Your browser is automatically speaking HTTP for you so that you don't have to.
Am I having a bit of a laugh? Maybe. But really, services should be user-agent agnostic. That's the whole "agent" part of User Agent and the founders of the Internet had incredible foresight to name it this way.
> Is it allowed to scrape data?
You mean, request data and receive what the other server voluntarily transmits?
> Are there any laws for this?
There was a court case that said the above is fine, thankfully, since that's how the internet works. There's probably other cases going on and I'm sure at least one of them will have some unfortunate tech-illiterate result that makes things worse for anyone who understands this stuff.
Yes, but it's not filling in the forms or clicking the buttons for me. HTTP is just infrastructure. Are LLMs infrastructure? Are we too maybe infrastructure? Where do we draw the line?
> You mean, request data and receive what the other server voluntarily transmits?
I mean to go over a large collection of publicly or privately (to you) available pages and parse and collect the data, with idea of using it in other purposes.
Regarding scraping, considering that this whole AI phase was built on illegal scraping, I don't think they can say anything now...
I've always called that "learning" but I guess it's called something else when a robot does it :)
Taking your position to its logical conclusion implies that we shouldn't try to mitigate DDoSes either.
In many cases, what the other server voluntarily transmits has so far been based on the tacit assumption that a person, with person-level time and computational power, is doing the receiving. While in principle a machine could be doing it even in pre-LLM times, in practice many websites, including all the biggest ones, have implemented a wide range of approaches to try to curb machine access, starting with user agent checks and rate limits but by no means ending there.
The question is: Given the new landscape, where this assumption increasingly does not hold (because AI agents are increasingly able to simulate anything a person could do online), would those servers voluntarily transmit that data? In many cases, the answer is no.
Not really. At any time you can, and should, choose not to reply to traffic that is wasting your bandwidth - ban IPs, use DDOS mitigation services, etc. My position is simply that regulation doesn't belong in this space, and it's ok for the 'net to be a dog eat dog world. Kind of what keeps technology advancing and exciting.
Is it me (the site owner in this example)? If so: Since it's my subjective decision to make, couldn't I equally legitimately decide that traffic I serve to non-human entities is "wasting my bandwidth"?
To be clear, I'm not trying to make the case that there should be some law in place that prevents scraping or machine access across the board -- only that it would make sense for website operators to be able, optionally, to include that kind of usage restriction in an ordinary contract and legally enforce it by the usual means (lawsuits), in addition to any kind of technical restrictions they are able to put in place.
The thing about most sites is they're public and you don't need to sign a real contract to use them. Can't have it both ways.
and at the same time, it feels like all the AI companies - not just elon - are doing everything they can to burn trust.
I almost wonder if this is a place where SpaceX, as an internet provider through starlink, has a unique advantage because websites are unable to block their networking as it could be residential starlink consumers.
i feel like there's an obvious advantage if your agent can work truly in the background
How does it work with login-walled sites like LinkedIn then? And what does "own computer" mean? X provisions a "private cloud" a'la Apple for your Bot?
https://image.non.io/4022ec77-be07-4baa-97e8-ad9d8d9aeb8a.we...
After you do you just tell the bot you're done logging in and it'll keep driving. And yea, it's a separate VM for each bot.
Source: had access for the last few weeks.
Tell me one reason why I would use this at my company? I basically have to bet on Grok being the best models for this.
Or I can use an open source version and use whatever model I want.
You see this with coding agents, everyone used Claude Code and then realized holy shit this is expensive and now use open source agents and they can use open source models and cut costs.
It's for this reason I am bullish on text formats in general. Or maybe sqlite wrappers where databases are necessary. But I want a separation between the worker and the work through some data contract that allows me to easily move my stuff around.
I believe the selling point here is these run on their own VMs, so you don't need to set up your own harnesses, models, and security infrastructure to run agents.
Historically people tend to pay for single-click commercial solutions for complex technical set ups like that.
The core is there. But there is some work to be done to have a nicer shell and all, which I’m currently focusing on.
However, no OpenAI API support (just Anthropic + openai.com) means I can’t use it for either.
More scams/spam, lower quality software everywhere, development is no longer fun, many interactions with coworkers are just "have my people talk to your people" behind the scenes, except it's "have my LLM read the huge document your LLM generated". Every business is trying to cut corners by using AI, so customer service sucks, products suck, prices are optimized to be the absolute maximum people will pay regardless of the actual value being provided (including food)...
As it's linked to an SMTP gateway I interact with it entirely by email. It also has API keys for my internal bug tracker, it has its own git forks of my repos and so on.
Over time it's improved itself so it has adaptive wakeups, a nice monitoring dashboard so I can see what it's doing if I want, a bunch of skills, a nightly wakeup to reorganize its home directories and so on. It keeps a private knowledge base in its home dir and writes its own skills, and it has a persistent todo list. When the todo list is populated it wakes up more frequently so it can break work up into chunks, a kind of basic Ralph loop.
I've found this email-centric paradigm works pretty nicely for me compared to just running a local CLI agent. For instance, I can assign a bug to "Axiom" (it named itself) in YouTrack and the email notification causes it to wake up and start work on the bug. If it gets blocked, it uses its API key to post a comment back to the ticket. If I think of something I just quickly email it, so I'm using Gmail instead of dealing with finicky ChatGPT style UIs that don't have good support for labelling, compact UI and other nice things.
On older models its judgement about what to work on wasn't that good, but with the latest GPTs it's doing much better. I just got back from holiday and it had triaged and resolved over 25 different bugs, a nice selection too.
Because the whole thing runs in a dedicated UNIX user account it is able to modify its own configuration, which has helped as I developed this setup.
However, based on the blog post, Grok Bot sounds a fair bit more sophisticated. I haven't felt a need for more than one bot as I can't easily saturate even a single bot.
Cost: just uses my regular ChatGPT Plus subscription, $20/month, plus of course the server it runs on (which is shared with lots of other stuff). I'm not working with it heavily, perhaps if I did I'd need the $200/month sub.
Either way, I still don't think that computer use is solved. It worked horribly on Codex and Antigravity the last time I tried. Maybe I was doing something wrong.
Although I'll probably never use Grok, this is an interesting release. I always thought GPT work and Claude Cowork are a bit awkward in their positioning. I'm still not sure what the real difference is with standard chat. This looks like the same thing with seamless memory and skills creation.
This seems like the middle ground between work mode and OpenClaw/Hermes (which I've never tried, too scared to mess something up). I think the humanization of the agents is cute and makes sense UX wise. I hope to see alternatives soon.
This is an interesting idea although I'm not sure how many companies are comfortable with giving SpaceXAI access to all your files and data. Outside of America this is, most likely, not going to fly.
It's not trivial to do, and I never managed to get bot-to-bot communication working. Even with my janky setup, the experience is honestly pretty great. Grok Bot simplifies the setup for this about as far as I imagine is possible, and frankly it's a pretty slick experience.
I fully expect this paradigm to catch on quickly.
Were you attempting to get them to message amongst themselves over Telegram, or something different?
with Grok, that's a tremendous assumption
Ah, you mean guardrails for _your_ protection...!
Dang - might be worth merging these two.
The other one feels pretty explicitly evil at this point.
GitHub gives 404 after logging in so I can’t event try it.
I wonder if they're going to try and compete against Slack with X.com chat?
They're clearly targeting less technical users but in exchange are asking you to upload every login you have to Elon's servers which is an insane thing to do imo. What a world where people are giving their Instagram sign in to the bot formerly known as mechahitler.