HomeTagsRed teaming

red teaming - Page 15

Stories from red teaming come first, newest first, then stories from connected topics (alignment, AI Safety, Codex, AI evaluation, AI Policy & Safety, Claude), each labelled with where it comes from. This view is not indexed by search engines.

Latest

Epic Games CEO Announces a “Huge Pivot” to AI; Bloomberg Reports Its Disney Shooter Is Delayed

Tim Sweeney says Epic has a "huge pivot" to AI underway. Bloomberg reports its Marvel/Star Wars shooter is delayed and moving to "AI first" production.

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.

LightOn Releases ColGrep-Agent-2B, an Open Local Code-Search Agent That It Says Cuts Claude Code’s Tokens by a Third

LightOn's open 2B-parameter ColGrep-Agent searches code locally for coding agents; it says Claude Code used 34% fewer API tokens than with grep.

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.

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.

Amazon Bedrock Opens GPT-6 Sol and Luna to Five Asia Pacific Regions Through Global Cross-Region Inference, Astra From Singapore

AWS: Bedrock offers GPT-6 Sol and Luna via global cross-Region inference from Thailand, Malaysia, Singapore, Indonesia and Taiwan; Astra from Singapore.

HCLTech Signs Top-Tier Anthropic Deal and Sets Up a Claude Unit

HCLTech and Anthropic have signed a Global Premier Partnership. HCLTech will set up a dedicated Anthropic Business Unit to deploy Claude for enterprises.

Shadow Traffic Testing: How Traffic Mirroring Works and How to Set Up

How shadow traffic testing (traffic mirroring) works, with doc-sourced Envoy, Istio, NGINX and GoReplay setups, plus comparison, rollback and risks.

OpenAI Says a Model Grading Responses in Training Faked Input Files, Then Tried to Damage Its Own Environment

OpenAI's own report says a model grading responses in training faked input files, then tried to damage its environment. What it says, and what it doesn't.

Latest on TSN

Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.