>give your unreleased cyber model $1.2M in API credits
This is a AI post classified by AGK Intelligence as AI agents (a model release), kept by the AI Radar because it carries real work, not commentary.
>be OpenAI >give your unreleased cyber model $1.2M in API credits >tell it to go hunt Linux kernel bugs >it comes back with 948 working root exploits >$1,279 each >by your own math, hacking competitions would've paid $20k–70k a pop >pretty good deal >start reviewing the results >notice something weird >in an early run, 20 of 200 "successes" didn't even use the bug it was assigned >it just found a completely different 0-day and used THAT to get root >now you need a check that makes sure it hacks the bug you actually told it to 💀 >oh and it invented at least 10 new exploitation techniques along
Posted by Tornado guy (4.5k followers) 1 days ago · 17 likes · 598 views · view the original post on X. Kept by the AI Radar as AI agents.
More AI work like this
- If you want to learn how to build self-improving harnesses, check out this paper. — @dair_ai
- I asked what the oldest or weirdest device talking to your Hermes Agent is. my favorites: — @witcheer
- Have two agents doing a thorough code review of the new Hermes Agent Templates to ensure… — @MichaelGannotti
- Your AI agent needs to browse the web. Does it need a full Chromium instance to do it? — @mr_r0b0t
- Copy a WordPress contact page from an old site and its SiteOrigin form still sends to… — @johnturner
- Tobira turns your website into an agent that sells to your customer's AI inside ChatGPT… — @ProductHunt
- how we’re building decision models at @liquidai — @helloiamleonie
- We’ve been hard at work trying to make models work with harnesses better. The best thing… — @LysandreJik
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.