Rendered at 23:47:05 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
jjcm 4 hours ago [-]
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.
pavel_lishin 2 hours ago [-]
> 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?
dylan604 6 minutes ago [-]
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 the 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 time. It's pretty much how things are done.
pavel_lishin 3 minutes ago [-]
> You will get a high percentage of requests that lead no where
Yes, but as per my last email, previously those were limited by the human scale of those requests.
raincole 2 hours ago [-]
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.
zeafoamrun 56 minutes ago [-]
It's crazy dude, whenever we put up a job ad it's filled with thousands of LLM generated fake candidates in a few days.
Looking at the examples they show here it is making more sense. Also where all the "content" on LinkedIn comes from.
aliasxneo 41 minutes ago [-]
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.
XCSme 51 minutes ago [-]
Will we have any way to know if a submission was done by a human or a bot?
dgellow 21 minutes ago [-]
LLM is really an anti human technology. The incentives that creates are terrible for society
slg 60 minutes ago [-]
Everything is becoming wildly inefficient, all in the name of improved efficiency.
dgellow 17 minutes ago [-]
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
tomrod 8 minutes ago [-]
AI Loopidity in other words
__xor_eax_eax 29 minutes ago [-]
We will soon be in a world where human to human communication is the only one that has value. Mark my words
jjcm 2 hours ago [-]
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.
pavel_lishin 2 hours ago [-]
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.
jbs789 57 minutes ago [-]
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.
XCSme 49 minutes ago [-]
Isn't a phone call like 10x more taxing than an email reply?
pavel_lishin 2 minutes ago [-]
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.
reaperducer 53 minutes ago [-]
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.
He left his phone number in his HN profile. Someone on HN should fire up a few thousand agents so he can personally learn what it's like to be on the receiving end of "efficiency" at "scale."
nvme0n1p1 5 minutes ago [-]
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.
aaron695 56 minutes ago [-]
[dead]
chasd00 1 hours ago [-]
Would be interesting to read a write up on this in detail. I have a similar use case I’ve been tasked to solve for a consulting client.
maherbeg 2 hours ago [-]
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.
anthonyskipper 1 hours ago [-]
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.
walrus01 12 minutes ago [-]
Oh boy, I've always wanted to give a gas turbine powered CSAM generator my credentials! I can't wait, sign me up now.
kylecazar 20 minutes ago [-]
I assume they store your session state/token for whatever SaaS it needs to work with but not the creds.
edoceo 31 minutes ago [-]
What? How? Just the x.com creds or other ones too?
drop_star 44 minutes ago [-]
So OpenClaw that steals your data and profiles you for the US gov. No thanks.
narrator 33 minutes ago [-]
A tool that only people who trust Elon can use.
XCSme 53 minutes ago [-]
The eternal fight between bots and anti-bot systems.
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...
akersten 49 minutes ago [-]
> 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.
XCSme 21 minutes ago [-]
> 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...
akoboldfrying 20 minutes ago [-]
> 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.
dgellow 6 hours ago [-]
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
walrus01 11 minutes ago [-]
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.
mike_hearn 3 hours ago [-]
They don't need to have access to your accounts. You can give them their own accounts.
FuckButtons 56 minutes ago [-]
Sure, but then what’s the use of them? Sounds like a very expensive tamagotchi.
napoleond 28 minutes ago [-]
Do your colleagues at work have access to all of your own accounts, or are they expensive tamagotchis?
FuckButtons 13 minutes ago [-]
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.
mvdtnz 12 minutes ago [-]
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?
walrus01 9 minutes ago [-]
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.
sixtyj 5 hours ago [-]
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.
shaism 2 hours ago [-]
According to Boris Cherny from Anthropic [1], the threat of prompt injection has been largely solved.
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.
andy99 1 hours ago [-]
They also don’t appear to consider false positives.
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.
samtp 2 hours ago [-]
"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.
stymaar 1 hours ago [-]
Largely solved in “it only happens 2% of the times now”.
Don't worry, you only have a 2% chance of having you bank account drained any time an attacker tries their chance.
WillMorr 8 minutes ago [-]
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.
dylanhouli 7 minutes ago [-]
I feel like we'd be better off if we just stopped at chatbots...why are we so eager to make the internet even more botted
whimsicalism 1 hours ago [-]
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.
theplumber 55 minutes ago [-]
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.
whimsicalism 24 minutes ago [-]
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.
kerv 2 hours ago [-]
Are there any opensource app/system that directly competes with a solution like this?
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.
natsucks 6 hours ago [-]
everyone is shipping their in house solutions and they all seem...kinda the same.
taoh 6 hours ago [-]
My feeling too. The foundation models and harnesses are commoditizing eventually because there's no stickiness nor algorithmic supersecrets.
bakies 2 hours ago [-]
Right... I've got this at home already
esafak 6 hours ago [-]
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!
mike_hearn 3 hours ago [-]
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.
wiradikusuma 4 hours ago [-]
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?
VariousPrograms 4 hours ago [-]
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.
jjcm 4 hours ago [-]
It'll ask you to take over its computer to log in:
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.
h14h 1 hours ago [-]
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.
Interesting that the pricing is "Cursor Ultra" and "Cursor Premium Teams." This very much feels like the Code --> Cowork product iteration.
jujube3 2 hours ago [-]
Grok lobster! (Rock lobster music starts playing)
LaurensBER 6 hours ago [-]
Pricing: 120/200 USD per month, per employee.
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.
KumaBear 1 hours ago [-]
The US government maybe? Wish I could type /s
surprisetalk 4 hours ago [-]
This seems like a very clever product move from X.ai
I wonder if they're going to try and compete against Slack with X.com chat?
jknoepfler 6 hours ago [-]
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.
Computer0 2 hours ago [-]
I am unsure if this is the end all be all but it appears preferable to claude code desktop to me.
basisword 6 hours ago [-]
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.
Cursor by inertia, but the X ownership is a big X against it...
Adrig 2 hours ago [-]
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
6 hours ago [-]
taoh 6 hours ago [-]
[flagged]
bakies 2 hours ago [-]
Curious how you've been living under that rock
justinhj 23 minutes ago [-]
They have simply been living outside your bubble
tuesdaynight 3 hours ago [-]
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
RunSet 2 hours ago [-]
Yes.
platevoltage 2 hours ago [-]
There's no way this is a real question.
slowmovintarget 5 hours ago [-]
[flagged]
barre 2 hours ago [-]
[flagged]
Uhhrrr 1 hours ago [-]
What nazi stuff did he post?
tonyhart7 6 hours ago [-]
so like OpenClaw ???
basisword 6 hours ago [-]
Like a hosted OpenClaw with, I assume, more guardrails.
I think perhaps I won't trust anything that ever gets released by this company, likely in perpetuity.
thih9 2 hours ago [-]
Anecdotally, same; recently I stopped using Cursor after learning that XAI now owns it.
agile-gift0262 2 hours ago [-]
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
whynotmaybe 1 hours ago [-]
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.
dyauspitr 2 hours ago [-]
Only thing I trusted was the “porn generator” on grok imagine because it was beyond good at what it did. They nerfed that so they’re back to nothing.
bilsbie 2 hours ago [-]
[flagged]
mexicocitinluez 1 hours ago [-]
Did that trigger you?
vorticalbox 6 hours ago [-]
GitHub login on iOS is just broken.
GitHub gives 404 after logging in so I can’t event try it.
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.
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?
Yes, but as per my last email, previously those were limited by the human scale of those requests.
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.
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 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.
He left his phone number in his HN profile. Someone on HN should fire up a few thousand agents so he can personally learn what it's like to be on the receiving end of "efficiency" at "scale."
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 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...
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.
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?
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.
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.
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.
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.
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.
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.
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.
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.
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 wonder if they're going to try and compete against Slack with X.com chat?
with Grok, that's a tremendous assumption
Ah, you mean guardrails for _your_ protection...!
Dang - might be worth merging these two.
GitHub gives 404 after logging in so I can’t event try it.
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.