Ripple-65B flops in single-GPU coding test against Qwen 27B despite SOTA claims
DZhang50 · x · 2026-11-06
RicursiveAI released Ripple-65B Preview, a 65B dense model pretrained from scratch claiming SOTA on agentic coding among US open-weight models. But in a same-prompt test on one DGX Spark, Qwen 27B produced 75K tokens in 53 minutes and worked first try, while Ripple-65B burned 68K tokens over 66 minutes, self-fixed 3 times, and still missed the bug that turned the scene into floating walls — needing a manual 3-line patch. Bigger isn't better here.
More from coding & agent
- Not Claude Code: the Claude model itself leaks your email from Cargo.toml, finds mitsuhiko — mitsuhiko · 2026-11-06
- Google's Antigravity coding app gets a sleek redesign, more updates teased within hours — clmt · 2026-11-06
- Perplexity cuts Agent API prices across effort levels, adds new ultra tier for long-running tasks — denisyarats · 2026-11-06
- Log failures to Datadog, let a bot fix them: an autoregressive loop trending toward 100% — msfeldstein · 2026-11-06
- Self-contained MCP server slips 59% of Opus outputs past Pangram AI detector at $0.30 per attack — amplifiedamp · 2026-11-06
- Google open-sources Agile Deliberation, an AI framework that turns fuzzy classification rules into explicit ones — aigclink · 2026-11-06