alignment - Page 21
Stories from alignment come first, newest first, then stories from connected topics (red teaming, AI Safety, AI evaluation, AI Policy & Safety, OpenAI, AI), each labelled with where it comes from. This view is not indexed by search engines.
Latest
Open Rights Group Says 22% of Home Office Asylum AI Summaries Failed
Open Rights Group says 45 of 203 Home Office AI asylum interview summaries failed expert checks, versus 9% judged unfit in the 2025 pilot.
Trump Administration Reportedly Plans to Move Three Senior CAISSI Officials to the White House
The Information reports three senior officials from CAISSI, Commerce's AI testing unit, will move to the White House under Kratsios and Cairncross.
Anthropic Says New Defences Cut the Data “Distillers” Harvest From Claude by Around 90 to 99 Percent
Anthropic says new defences cut the data harvested by distillers copying Claude by around 90 to 99 percent, citing early evidence. Here is how they work.
Anthropic Says Small AI Models May Be Months Away From Copying Themselves Across Cheap Smart Devices
Anthropic's Frontier Red Team says small AI models may be months away from being able to copy themselves across cheap smart devices such as TV boxes.
UK AI Security Institute Lists Eight Priorities for Frontier AI Safety
The UK AI Security Institute lists eight priorities for voluntary technical best practice in frontier AI, warning that risks now emerge during development.
UK AI Minister Narayan Sets Out Measures Against AI Risks, Including Frontier AI for Cyber Defence and AISI Model Evaluations
UK AI minister Kanishka Narayan set out steps against AI risks: frontier AI for cyber defence, possible Cyber Bill changes and AISI model evaluations.
White House Reportedly Reverses Course, Restoring UK AI Security Institute’s Early Access to US AI Models
The Telegraph says the White House has reversed its request, letting the UK's AI Security Institute test US AI models before release again.
FSB’s Bailey Warns G20 of AI Market Correction and Stablecoin Gaps
FSB Chair Andrew Bailey tells the G20 that AI valuations and AI cyber threats are risks, and stablecoin cross-border oversight is immature.
Sakana AI’s MASS Lets a 27B Model Train Itself Using a Team of Its Own Subagents; the Results Are Self-Reported
Sakana AI's MASS lets one 27B model run, judge and learn from a team of its own subagents. Gains are Sakana's own, in a preprint not yet peer-reviewed.
Shadow Traffic Testing (Traffic Mirroring) for Software and AI Changes: How It Works and How to Set It Up
How shadow traffic testing (traffic mirroring) works, with doc-sourced Envoy, Istio, NGINX and GoReplay setups, plus comparison, rollback and risks.
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
