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

181–190 of 362 posts

Re: Grok Bot

#181

Post by s900mhz »

whimsicalism wrote: post #115
edot wrote: post #112

Earlier quoted context omitted.

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

I agree, but I made myself laugh pondering a solution to this in which I came up with a Raspberry Pi like device that acts as the loopback for the agent. Always keep it on and plugged in.

I would like to introduce the Grok Box

Re: Grok Bot

#182

Post by kkotak »

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.

It's already a bot eats bot world.

Re: Grok Bot

#183

Post by lachlanj »

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

Amazing! I guess we’ll never see another prompt injection again

Re: Grok Bot

#184

Post by taoh »

bakies wrote: post #42
taoh wrote: post #13

Earlier quoted context omitted.

[flagged]

[flagged]

I was merely asking a question. I'm not a native English speaker so if my comments sounded offending, I didn't mean it. I don't follow Musk on X. I have no political interests. I read news about SpaceX, Tesla, and X and that's it. I'm focusing on building my own product and company. Just somehow curious when I read the previous comments so I asked.

Re: Grok Bot

#185

Post by taoh »

tuesdaynight wrote: post #31
taoh wrote: post #13

Earlier quoted context omitted.

[flagged]

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

I don't follow him. Sometimes he appeared on my timeline and I skimmed through. I don't agree or disagree with him strongly. There are some companies that will use or avoid certain products or people. Thus there was my question. If the question looked political, it wasn't my intention. Thx.

Re: Grok Bot

#186

Post by saidinesh5 »

slg wrote: post #70
raincole wrote: post #46

Earlier quoted context omitted.

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.

Everything is becoming wildly inefficient, all in the name of improved efficiency.

I think that's just the phase 1? Once we have all the use cases figured out, optimizations gradually follow?

Re: Grok Bot

#187

Post by kkotak »

yellow_postit wrote: post #120
mvdtnz wrote: post #95

Earlier quoted context omitted.

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 is the growing pain of any “employer” and I suspect lots of startups and features coming to fill the void. 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!

The issue is not just bank or CC accounts, but your personal data accounts (Email, photos, SMS, calendar, documents, etc.) that give the necessary context to the agent to do useful work for you. That's where the problem lies.

Re: Grok Bot

#188

Post by sigmarule »

rootusrootus wrote: post #179
whynotmaybe wrote: post #69

Earlier quoted context omitted.

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.

Perhaps people are deciding that the impact a nefarious foreign government can have on them is less of a risk than their own government acting the same way. So Chinese should feel safer interacting with American companies and Americans safer interacting with Chinese companies. That's probably bullshit. Could also just be yet another wave of information warfare. I'm like 87.9% sure that bad actors explains nearly ever…

On a personal level, your own government can absolutely, 100% be more likely to do you harm than a foreign government, for simple jurisdictional reasons. They have more power over your life. And with an administration as corrupt and degenerate as the current US administration, it's an extremely reasonable perspective to have.

Re: Grok Bot

#189

Post by eloisius »

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.

The inundation of AI applications is shitty, but I think this side of the coin—AI interviewer—is even worse. This is degrading for a human applicant, and after the very immediate term it’s probably not going to be very useful. Instead of grinding leetcode, people are going to be grinding the AI interview, which is depressing to even consider. Not only that, but there’s also going to be an arms race of AI tools that can ace the AI interview for you.

Re: Grok Bot

#190

Post by human305893 »

XCSme wrote: post #79
jbs789 wrote: post #71

Earlier quoted context omitted.

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.

Isn't a phone call like 10x more taxing than an email reply?

For every meeting that could have been an email. There are 30 back and forth emails that could have been a 5 min phone call.
Post reply on HN