Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Grok Bot

x.ai

Post reply on HN
Print view View original

221–230 of 362 posts

Re: Grok Bot

#221

Post by 0x3f »

miguelspizza wrote: post #219
anthonyskipper wrote: post #60

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.

AI Session Hijacking is such a dead end and I think this will be the thing that kills it. Just register these things in the IDP and let them sign into their own accounts. Maybe if we give these things their own identity people will stop letting their AIs post as them in linkedin

> Just register these things in the IDP and let them sign into their own accounts.

And when you get blocked by whatever anti-bot tech the site is running?

Re: Grok Bot

#222

Post by taneq »

r3trohack3r wrote: post #155
solid_fuel wrote: post #110

Earlier quoted context omitted.

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.

> The user without empathy has managed to save 30 minutes on a task One supplier ended up with a direct sale they wouldn’t have otherwise

Normally you’d get 2-3 quotes, meaning suppliers would on average get a sale for every few RFQs they respond to.

Now guys like this twiddle one knob and generate 20x as much RFQ spam, costing suppliers 20x as much. It’s tantamount to a DoS attack.

Re: Grok Bot

#223

Post by plomme »

shaism wrote: post #49
sixtyj wrote: post #20

Earlier quoted context omitted.

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.

According to Boris Cherny from Anthropic [1], the threat of prompt injection has been largely solved. [1]: https://x.com/bcherny/status/2086520950259118464

To paraphrase a famous quote: You have to be lucky every time, an attacker only has to be lucky once.

Re: Grok Bot

#224

Post by bulder »

ralph84 wrote: post #203
stillpointlab wrote: post #171

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…

How does per-seat pricing work against bots? If anything it's a great deal because SaaS providers set per-seat pricing with the expectation that on average most seats are idle. Bots working 24x7 can get a lot more value out of a seat than humans working 9-5.

Presumably it'll either mean selling "agent seats", or billing seats for every started hour of use. With a monthly minimum, of course.

Re: Grok Bot

#225

Post by xdertz »

napoleond wrote: post #86
FuckButtons wrote: post #73

Earlier quoted context omitted.

Sure, but then what’s the use of them? Sounds like a very expensive tamagotchi.

Do your colleagues at work have access to all of your own accounts, or are they expensive tamagotchis?

when my colleagues do something illegal or negligent they are personally on the hook for it. Who is on the hook when my bot does that?

Re: Grok Bot

#226

Post by Bombthecat »

pavel_lishin wrote: post #35
jjcm wrote: post #23

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…

> 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 fiv…

You need bots on th other side too. Simple

Re: Grok Bot

#227

Post by xdertz »

mvdtnz wrote: post #95
mike_hearn wrote: post #30

Earlier quoted context omitted.

They don't need to have access to your accounts. You can give them their own accounts.

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?

This sounds like a problem the service providers should solve. Some kind of 'create bot account' function where you can give granular permissions for a new account to interact with your data. This already exists in some form with company accounts.

Re: Grok Bot

#228

Post by FridgeSeal »

elwebmaster wrote: post #157
XCSme wrote: post #78

Earlier quoted context omitted.

Will we have any way to know if a submission was done by a human or a bot?

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.

Where do you work?

Mostly so that I can know to never apply, because that application process sounds awful and degrading.

Re: Grok Bot

#229

Post by cm2187 »

raincole wrote: post #46
pavel_lishin wrote: post #35

Earlier quoted context omitted.

> 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 fiv…

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.

MCP servers everywhere rather. You automate your life with a bot, the bot interacts with the world through MCP servers (or their successor). The MCP servers themselves may have been implemented by bots but AI to AI is unnecessary wasteful.
Post reply on HN