Stories by zachdotai

AI evaluation startup Braintrust confirms breach

I built an agent that breaks your AI agents before someone else does

Bret Taylor's Sierra Buys YC-Backed AI Startup Fragment

Show HN: Nyx – multi-turn, adaptive, offensive testing harness for AI agents

Workshop Labs Is Joining Thinking Machines

Show HN: ACE – A dynamic benchmark measuring the cost to break AI agents

We've had more AI security incidents in 2026 than all of 2024

NeurIPS Tightens Sanctions Compliance

SWE-bench will hit 90% this year

Cursor trained Composer to self-summarize through RL instead of a prompt

Stripe-backed startup Tempo releases the Machine Payments Protocol

Show HN: Open-source playground to red-team AI agents with exploits published

Weekly "Wordle" for Breaking AI Agents

My First AI Bug Bounty – A Technique for AI Recon – Peter Hendy

Expanding our long-running agents research preview · Cursor

Weekly "Wordle" for Breaking AI Agents

AI agents are easy to break

Show HN: Fabraix Playground – Weekly Wordle for Breaking AI Agents

Show HN: GX CLI – Automatically stack large PRs to ship faster