MaxxBench exposes DeepSWE overfitting in AI coding models
Mutations to DeepSWE tasks cause large performance drops in models due to benchmark overfitting.
30
AI model
Muse Spark 1.2
- Mentions · 7d1
- Mentions · 30d1
- All mentions2
- First seenOct 2, 2026
- Last mentioned1d ago
Timeline
2 articles · newest firstRolling the cyber dice with open-source and open-weight AI models
Open-weight AI models can hide backdoors and poisoning that scanners miss, shifting breach liability onto security leaders.
39
Appears with
- DeepSeek V4 Flashai model · 1
- Anthropicorganization · 1
- JFrogorganization · 1
- GPT-5.6 Solai model · 1
- Hugging Faceorganization · 1
- Anthropicvendor · 1
- GPT-6 Astraai model · 1
- DeepSeek V4.1 Flashai model · 1
- Gemini 3.8 Flashai model · 1
- Muse Glimmerai model · 1
- GPT-5.6 Lunaai model · 1
- GLM-5.3ai model · 1
- Claude Opus 5ai model · 1
- Metaorganization · 1
- OpenAIvendor · 1
- Metavendor · 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.