Astra hits 75% on 3x3 determinants — likely a dedicated circuit, not a general algorithm
justanotherlaw · x · 2026-09-26
Analyzing the model Astra's small-determinant performance, the author speculates it has a circuit specific to 3x3 matrices (very common in training data) rather than a general small-determinant algorithm — otherwise its accuracy wouldn't drop to 75% on single 4x4 cases.
The thread rules out randomness and focuses on distinguishing a specialized circuit from a general algorithm.
More from Models
- Fable 5.2 hands-on: great at well-defined hard problems, best since GPT 6 Astra — rachittshah · 2026-11-11
- The next AI vendor lock-in won't be the model API, it'll be the harness — Arindam_1729 · 2026-11-11
- Leaked: OpenAI's GPT-6.2 (codename betelgeuse) reportedly weighs in at ~15T tokens, drops Thursday — iruletheworldmo · 2026-11-11
- Running DeepSeek 4.1 locally on an $800 rig with a used RTX 3090 at 2-3 tok/s — LankyGuitar6528 · 2026-11-11
- Google open-sources Harness², an agent that rewrites its own setup per task — Arindam_1729 · 2026-11-11
- Dev dumps Codex desktop app over quality issues, falls back to codex-cli — tekbog · 2026-11-11