Skill adaptation improves weak models in harness self-evolution
Across 103 task-skill pairs, skills that raise GPT-5.6-luna by 31.1 points lower Gemma-4-E4B by 8.8.
48
AI model
Kimi-K2.5
- Mentions · 7d0
- Mentions · 30d1
- All mentions1
- First seenOct 9, 2026
- Last mentioned21d ago
Timeline
1 articles · newest firstAppears with
- GPT-5.6-lunaai model · 1
- Gemma-4-E4Bai model · 1
- Kimi-K3ai model · 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.