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
Organization
Booz Allen
- Mentions · 7d2
- Mentions · 30d9
- All mentions10
- First seenSep 2, 2026
- Last mentioned2d ago
Timeline
10 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
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
AI Takes Control of Robotic Arm in 16 Minutes Flat
Booz Allen lab tests showed frontier AI models can seize an OT robotic arm in 16 minutes.
66
AI Agents Navigate Unfamiliar OT Systems and Move Equipment in Minutes, Booz Allen Finds
Booz Allen lab tests show frontier AI agents can traverse unfamiliar OT networks and move equipment within minutes.
66
Frontier AI cleared every OT attack goal Booz Allen set in its lab
Booz Allen says frontier AI models completed every OT attack goal in its isolated factory lab, including moving a robotic arm.
71
Anthropic Fast-Tracks AI Bug Reports to OSS Maintainers, Taps 11 Firms for OT Security
Anthropic launched unreviewed AI vulnerability reports for OSS maintainers and an OT security program with 11 firms.
64
Anthropic Cyber Mission to Support Defenders with Tools, Research, and Resources
Anthropic launched a Cyber Mission pairing Claude, engineers, and partners to defend critical infrastructure and open-source projects.
65
Anthropic rolls out program for ‘long-term commitment’ to secure critical infrastructure, open source software
Anthropic launched a program pairing Claude with security firms to find and fix flaws in critical infrastructure and open-source software.
64
Claude Mythos only model to complete full cyber kill chain, experts say
Booz Allen's Cyber Weapon Index finds only Claude Mythos completed an autonomous full cyber kill chain; mainstream AI-driven attacks deemed imminent.
79
Appears with
- Dragosorganization · 5
- CrowdStrikeorganization · 5
- Anthropicvendor · 4
- Claudeai model · 4
- Alibabavendor · 4
- Hitachiorganization · 3
- Claudeproduct · 3
- Qwen3-Coderai model · 3
- Accentureorganization · 3
- Nozomi Networksorganization · 3
- Palo Alto Networksorganization · 3
- Deloitteorganization · 3
- PwCorganization · 3
- Insane Cyberorganization · 3
- OSS Scannerproduct · 2
- OpenAIorganization · 2
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.