I used to think if all else fails I'd take the path of a Cynic and retire in a giant vase. I'm not quite sure anymore. If you're done with society and the world you might as well prompt inject from a beach somewhere, and we're so not ready for this.
Grok Bot
211–220 of 362 posts
Re: Grok Bot
#212Earlier 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.
Like payment networks? I dunno, this just seems like commerce to me. If the inference doesn't return value it won't be used
Re: Grok Bot
#213Earlier quoted context omitted.
According to Boris Cherny from Anthropic [1], the threat of prompt injection has been largely solved. [1]: https://x.com/bcherny/status/2086520950259118464
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.
Yeah, sadly data and command intermingling are also one of the main things that make these "AI" appear so human.
Humans are also susceptible to prompt injection all the time, we just call it differently: social engineering or scam.
Re: Grok Bot
#214Are there any opensource app/system that directly competes with a solution like this?
Grokbot is another derivative of open source originals like Open Claw
Re: Grok Bot
#215Earlier quoted context omitted.
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.…
Those businesses are welcome to publish their prices if they want to avoid that
Not really practical for custom work.
Re: Grok Bot
#216Earlier quoted context omitted.
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 have a hard time looking at the world around me and thinking "close to no value"
I’m talking specifically about the AI industry
Re: Grok Bot
#217Earlier quoted context omitted.
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.
So why didn't you just do it manually? Why use an agent in the first place?
Poor UX. The internet used to be designed around ease of use. Now it's dark patterns, advertising, nag windows, and "engagement." Retailers don't offer a way to aggregate info easily, so it means wading through piles of shit to find relevant information. Bots can eliminate all the shitty parts about using the internet. That's a big time saver, but it's also a big headache saver.
Re: Grok Bot
#218I'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've used less tokens in the last 5 years prior to this month than I have this month.
So using a bot is almost like having an employee, but instead of a fixed salary, or even an hourly rate, they will just invoice you for whatever they think is necessary to do the tasks you give them? And agents can be very creative when coming up with ways to spend tokens...
Re: Grok Bot
#219The 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
Re: Grok Bot
#220My initial impression is strong: Agent-to-Agent comms are clearly a first-class citizen of this tech. There's a cohesion that's palpable. Maybe it just fits my workflow better than other tools. I have some routines set up for tomorrow morning that will tell me if the juice is worth the squeeze. 48% weekly usage left after 3 hours of experimenting, tough.
What plan are you on? Does the bot have its own usage, or does it count against cursor/grok code usage?