User says Claude Opus 5 still lags, preferring Opus 4.6 in their harness
sachdh · x · 2026-07-29
A user says Claude Opus 5 is not living up to the recursion/self-improvement rhetoric.
- After testing Opus 4.7, they immediately returned to Opus 4.6.
- In their harness, Opus 4.6 + custom tooling allegedly outperforms Opus 4.8 by a wide margin.
- The jab lands directly on Anthropic’s own post about recursive self-improvement and the need to slow frontier AI development.
More from Models
- User reverses course and says GPT 5.6 Sol is actually a really good model — TheZachMueller · 2026-07-29
- Sam Altman teases GPT-5.6 Sol on Cerebras at 750 tokens/sec in July — daniel_mac8 · 2026-07-29
- Grok 4.5 Medium tops LaurenBench with 56.9%, ahead of Claude Sonnet 5 and GLM 5.2 — elonmusk · 2026-07-29
- A viral chart compares 12 paid AI tools with free replacements — nikola_mr64990 · 2026-07-29
- Verdent Partners with Moonshot to Optimize Agentic Coding for 2.8T-param Kimi K3 — PrajwalTomar_ · 2026-07-29
- Best Local Models Under 120B: Are Qwen Series the Only Answer? — Possible_Grocery8079 · 2026-07-29