mitsuhiko dislikes GPT 6 Astra's C code: hard to read and weirdly token-efficient
mitsuhiko · x · 2026-09-27
Responding to antirez's suggestion to write C with Astra, mitsuhiko says he dislikes Astra's C output: in a small game side project he often finds the code hard to read, with the model frequently falling into "token efficient goal seeking patterns" he really hates.
More from Models
- rasbt and marlene_zw break down Claude watermarks, reasoning models in new TechTalk — marlene_zw · 2026-09-27
- Opus 5.5 praised as remarkably efficient: top-tier quality at surprisingly good rates — kimmonismus · 2026-09-27
- Local AI community urges Qwen to bring back a 35B-class MoE for low-VRAM GPUs — julianharris · 2026-09-27
- Grok 4.7 lifts Terminal-Bench 4.0 from 20.3% to 38%, but burns 125% more output tokens — dl_weekly · 2026-09-27
- TypeSafe's Jev: A Decision-Only Model That Returns Typed Choices Instead of Generated Text — Rahulstark2 · 2026-09-27
- Codex team hints point to speed — GPT-6 Astra on Cerebras rumored — haider1 · 2026-09-27