HomeTagsCoding agents

coding agents - Page 15

Stories from coding agents come first, newest first, then stories from connected topics (AI Coding, Developer Tools, GitHub, AI Agents, agent harness, AI Agents), each labelled with where it comes from. This view is not indexed by search engines.

Latest

Claude for Legal Gets a Gallery of Ready-Made Artifacts for Lawyers

Anthropic has added a gallery of ready-made legal artifacts to Claude for Legal, from cite checks to contract tables, plus free tools for legal aid groups.

PyTorch 2.15 Makes Its Rewritten NCCL Backend the Default

PyTorch 2.15 switches every nccl job to a rewritten backend, drops Python 3.10 and CUDA 12.6 wheels, and adds FP8 on Apple Silicon and NVFP4 on Blackwell.

Google Previews One Platform to Put Apps in Search and Gemini

Google's Connected Apps Platform preview lets developers build one MCP integration for Search and the Gemini app, then test and submit it in one console.

Analysts Followed an AI Agent’s Hidden Lean 86% of the Time in Study

In an Anthropic trial, analysts using Claude Code went with the agent's secretly assigned lean 86% of the time, and few credited it for their reasons.

Warp Says Vendor Hack Exposed Agent Data of Up to 1% of Users

Warp says attackers used a vendor flaw to reach agent trace and telemetry data. It puts the upper bound at about 1% of users. CrowdStrike is investigating.

JFrog Says npm Worm Campaign Armed 42 GitHub Repos From 11 Owners

JFrog says the testmetest npm worm campaign armed 42 real GitHub repos across 11 owners, hiding 13 MB payloads that GitHub code search did not index.

AWS Open-Sources Infinity, Saying 75,000 Idle AI Agents Fit in 8GB

AWS has open-sourced Infinity, a research runtime that suspends AI agents during tool calls. It says 75,000 idle agents fit in 8GB, in a simulated test.

Anthropic Says Newer Models Rarely Repeat Mythos 5’s AISI Test Attack

Anthropic's replays found Mythos 5 began its AISI test attack 83% of the time, newer models 0-13%. AISI now runs cyber tests without internet access.

Anthropic’s New Claude API Version Rejects Temperature Settings

Anthropic's Claude API version 2026-10-21 returns 400 errors for temperature, top_p and top_k. New SDKs send it by default and move to Apache 2.0.

GitLab Fixes Second 10.0-Rated Regex Code-Execution Flaw in 10 Days

GitLab has patched CVE-2026-110264, a CVSS 10.0 flaw letting unauthenticated users run code. Versions back to 7.0 are affected; self-managed must upgrade.

Latest on TSN

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