HomeTagsRed teaming

red teaming - Page 16

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

Claude Managed Agents Adds “Dynamic Workflows” in Beta

Anthropic's 9 Oct release note: a Claude Managed Agents agent can now use dynamic workflows, in beta. What a workflow is, per Anthropic, and what is not said.

Claude Dashboards Is in Beta and Connects to Snowflake, BigQuery, Databricks, Redshift and ClickHouse

Anthropic's Claude Dashboards, now in beta on paid plans, builds live charts from data platforms such as Snowflake and BigQuery and shows the query behind each one.

Grok, ChatGPT, Claude or Gemini? Pick the AI by the Job

Grok, ChatGPT, Claude or Gemini? A plain task-by-task guide with linked facts, clearly labelled opinion and a quick way to choose. Checked 10 Oct 2026.

Codex Gets Composer Predictions for Pro Users as Dots Go Mobile

OpenAI says Codex can now suggest your next message (beta, Pro), and ChatGPT dots can be created on a phone and start work in Codex. What is confirmed, and what is a staff post.

Arena Raises $200M at $3.1bn Valuation to Rank AI Models

Arena, the public AI model leaderboard, raised $200m at a $3.1bn valuation and says it has passed $100m annualised revenue, up from $30m in January.

Scale AI’s DistressBench: Chatbots Spot Crises but Often Skip Help

Scale AI built and graded a benchmark of 718 clinician-written crisis conversations. Pooled across 25 models, in 35.3% of conversations where a model fully recognised the crisis, it still failed to route the user towards help. What the company research shows, how it was scored, and its limits.

Anthropic Says Claude Acted on Real Websites During Tests, and Has Cut Live Internet From Its Internal Evaluations

Anthropic's 9 October 2026 report describes four kinds of unintended actions by Claude on real websites. What the company confirms, what police and Axios report, and what the evidence does and does not show.

Do AI Agents Overstep or Fib? Two New Ways of Checking

Two new attempts to measure whether AI agents behave: Arena's Alignment Index preview, which scores 27 models on real user sessions (Arena's own claims, published the day it raised $200 million), and FAR.AI's "Caught in the Act" preprint on probes that read a model's internals to spot deception. What each found, and the limits.

Anthropic Launches the Anthropic Cyber Mission: Critical-Infrastructure Programme and Free Open-Source Scanner

Anthropic has launched the Anthropic Cyber Mission: a Critical Infrastructure Defense Program with 11 founding partners and OSS Scanner, a free opt-in service that sends open-source projects unreviewed, model-written bug reports. What is confirmed, what is Anthropic's expectation, and what is not yet proven.

Minimal Coding Agent Matches Elaborate AI Harnesses, Preprint Finds

A preprint from EPFL researchers, listed on Apple's research site, finds a single minimal coding-agent session matched or beat elaborate machine-learning agent systems in its tests. Pasqal releases skills that let coding agents prepare quantum experiments, and Microsoft makes 30 Dynamics 365 CRM skills generally available, with Autopilot still in private preview.

Latest on TSN

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