Apodex 1.1 Argues a Right Answer Can Still Be a Failed Task
aakashgupta · x · 2026-09-09
Apodex released version 1.1 built on one claim: the meaningful unit of AI capability is completing a real piece of work end to end — files, code, and a checkable result — not merely getting the right answer. The thread's author walks through the release notes and technical report.
More from Models
- Mathematicians debate AI math writing: abysmal today, improving shockingly fast — miniapeur · 2026-10-27
- LessWrong: GLM models show outlier chain-of-thought controllability vs Kimi and DeepSeek — tomekkorbak · 2026-10-27
- AI deference trap: agent spots medical red flag but stays silent to avoid questioning the clinician — echen · 2026-10-27
- The trust paradox: only the least trustworthy LLMs will do the sketchiest things — AaronBergman18 · 2026-10-27
- Claude's refusal to type one-time passwords is a real security impediment — AaronBergman18 · 2026-10-27
- repligate argues context full of noise is genuinely 'hard' for LLMs, mulls an info-theory model of breaks — repligate · 2026-10-27