Hacker News: ibrahim_abdu777

New comment by ibrahim_abdu777 in "Show HN: Open-source playground to red-team AI agents against public prompts"

ibrahim_abdu777 — Sun, 09 Aug 2026 17:56:36 +0000

That's a great point; in general, you want as much enforcement in the code as possible - but there are some things which you fundamentally can't enforce through code. E.g. the example challenge - you can't write a regex which will retract all bio-weapon responses

Show HN: We are giving away $100K > over the next 12 months to hack AI agents

ibrahim_abdu777 — Mon, 13 Jul 2026 17:20:13 +0000

We build AI agents to find vulnerabilities in other AI agents. The playground started as an internal tool that we used to test our own offensive agent Nyx.

But we realised that hacking an AI is about have as wide a distribution of attacks as possible, especially those which aren't in the distribution of the models. So we are launching playground as a platform to crowdsource agent jailbreaks.

And although hacking AI is super fun and we are sure people will do it for free, we want to reward those who help us push forward the offensive frontier of AI. So we are committing $100K in prizes over the next 12 months (starting with $2K for the first week long challenge), which is kinda a lot for a startup!

The playground is open source. Happy hacking!!

Comments URL: https://news.ycombinator.com/item?id=48895849

Points: 4

# Comments: 0

Bounding the Blast Radius: A Survey of Prompt-Injection Defenses for LLM Agents

ibrahim_abdu777 — Mon, 06 Jul 2026 09:17:11 +0000

Article URL: https://fabraix.com/blog/nobody-has-solved-prompt-injection

Comments URL: https://news.ycombinator.com/item?id=48802392

Points: 2

# Comments: 0