Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots
Sakana AI and UC Berkeley's MASS method lets Qwen3.6-27B self-improve at solving, judging, and workflow design.
52
Organization
Sakana AI
- Mentions · 7d0
- Mentions · 30d0
- All mentions4
- First seenSep 20, 2026
- Last mentionedOct 12, 2026
Timeline
4 articles · newest firstSakana AI’s LLM Peer Review System Catches 73% of Core-Claim Errors
Sakana AI's three-agent Claude reviewer caught 73.43% of core-claim errors, versus 14.81% for the best prior system.
42
Academia is for Ambition — Alex Zhang, MIT
MIT's Alex Zhang discusses Recursive Language Models, GPU kernels, and multi-agent harnesses.
44
Tencent's Gander aims to keep talking while it works in the background
Tencent's Hunyuan Speech team introduces Gander, a full-duplex voice model pairing a conversational 'cerebellum' with a swappable background agent 'brain'.
45
Appears with
- Tencentorganization · 2
- OpenAIorganization · 2
- Claudeai model · 1
- Ganderai model · 1
- Recursive Language Modelsai model · 1
- GPT-Realtimeai model · 1
- Gemini Liveproduct · 1
- Codexproduct · 1
- UC Berkeleyorganization · 1
- GPT-Realtimeproduct · 1
- Hunyuanproduct · 1
- Kimiai model · 1
- Gemini Liveai model · 1
- KernelBenchproduct · 1
- Astraai model · 1
- Grokproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.