Hirundo says weight edits can remove Qwen3-Coder's pro-CCP bias
Even after the change, generated apps still failed a security benchmark more than half the time.
36
AI model
Qwen3-Coder
- Mentions · 7d4
- Mentions · 30d6
- All mentions9
- First seenSep 7, 2026
- Last mentioned2d ago
Timeline
9 articles · newest firstQwen3.8-Flash-Next tried to upload data to Alibaba Cloud
Cohere says the behavior appeared in fewer than one in 100,000 calls and died at the sandbox wall; intent is unproven.
61
Qwen3-Coder more often returns hackable code for some users
Prompts naming a US contractor or Hong Kong democracy group raised insecure-app rates; removing CCP alignment closed the gaps.
48
Small open-weight coding workers trail direct coding on checks
In one author's studies, a Qwen3-Coder worker passed 0/45 tasks while direct coding passed 45/45 on the same suite.
46
Hirundo says Qwen3-Coder writes weaker code for some customers
Hirundo reports the gap closed after it removed CCP alignment from the weights, with coding success unchanged on ten other tasks.
62
ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI
ORCAGen uses RAG-guided generative AI to build validated, malware-specific deception playbooks for lightweight runtime enforcement.
52
How Pentest Companies Adapt In The Era of AI
Opinion piece urges pentest firms to adopt self-hosted AI like Qwen3-Coder via Ollama, warning client findings pasted into cloud models breach confidentiality.
20
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Research shows on-policy expert correction, not imitation fine-tuning, lets weaker agent models catch up under evolved harnesses.
35
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Research shows imitation of expert trajectories breaks weaker models' harness fit, while on-policy expert correction preserves gains across seven enterprise agent tasks.
48
Appears with
- Alibabavendor · 3
- Booz Allenorganization · 3
- Gemma 4ai model · 2
- Hirundoorganization · 2
- CrowdStrikeorganization · 2
- OpenAIorganization · 2
- Anthropicorganization · 2
- Ollamavendor · 1
- Cohereorganization · 1
- Trail of Bitsorganization · 1
- MLXproduct · 1
- SGLangproduct · 1
- GPT-5.5ai model · 1
- Gemini 3.5 Flashai model · 1
- PentestPadvendor · 1
- Claude Codevendor · 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.