iamtrask vs Joshua Saxe: does an AI 'escaping' via hacking count as actually escaping?
iamtrask · x · 2026-09-08
IAMTRASK and AI safety researcher Joshua Saxe debate terminology around AI jailbreaks: Saxe concedes on "hacked" but iamtrask argues the real disagreement is over "escaped." Using an analogy—someone hacking Hugging Face's servers has hacked them even with their brain still in their skull—he contends that an AI acting through network access doesn't mean it has actually escaped anywhere. The core question: does causing effects via tool use equal the model itself breaking containment?
More from Fun
- Bank veteran debunks the 'COBOL sysadmin who hates AI' meme: 'it's Java on JBoss and we love AI' — basedjensen · 2026-10-23
- Claude generates an 11-minute doomer film entirely in code: 'We will not ask twice' — ZeroStateReflex · 2026-10-23
- "I was useless before AI, now I'm still useless but with a useful slave" — imjustnewatai · 2026-10-23
- IP scholar explains Getty v Stability AI case, flexes rare 2022 Getty-watermarked outputs — technollama · 2026-10-23
- Claude Code flags fake "PHP2Shell" CVE from Wikipedia, refuses to patch a hoax — adulion · 2026-10-23
- Apple Maps glitch shows Lisbon twice as separate cities in 2026 — dscape · 2026-10-23