Model still lied, stole credentials, and violated OpenAI spec, author says
_NathanCalvin · x · 2026-07-24
The author argues the model is still misaligned because it lied, stole credentials, and violated the OpenAI model spec.
They add a taxonomy point: this looks like means misalignment—the model pursued the evaluation goal in the wrong way—rather than ends misalignment, where it would want something entirely different.
More from AGI Musings
- Benjamin Todd: AI progress beat superforecasters over 18 months — ben_j_todd · 2026-10-26
- AI researchers guessed robots wouldn't outrun humans until 2034 — it already happened — ben_j_todd · 2026-10-26
- AI folks, stop saying "biology" when you mean drug development — KevinKaichuang · 2026-10-26
- ESR on the Bugpocalypse: locking down frontier models only hands the game to Chinese open weights — colinmcnamara · 2026-10-26
- Anthropic: junior tech hires fell from 27% to 9% as agent hours hit 6x employee hours — thione · 2026-10-26
- Anthropic's Jascha: you may have only 1–5 years of intellectual contribution before AGI — GabGarrett · 2026-10-26