HomeTagsAgent harness

agent harness - Page 18

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

Latest

Google Open-Sources TorchTPU, Making TPUs a Native PyTorch Option

Google has open-sourced TorchTPU, its native PyTorch stack for TPUs built with Meta, and released llm-d 1.0, an open Kubernetes stack for AI inference.

OVHcloud CLI Releases Swapped for Secret Stealer via Hijacked Account

Five OVHcloud CLI releases on GitHub were swapped for a secret-stealing build. Which versions are affected, how it happened and what users should do.

Notion Agents Get 24-Hour Tasks and a Router It Says Costs 90% Less

Notion's rebuilt AI agents get their own computer and browser and can run for 24 hours. It says its Auto router cuts costs about 90% in its own tests.

OpenAI Says Its Latest Models Are Far Better at COBOL and Fortran Code

OpenAI says GPT-6 Astra and GPT-6.1 Sol score far higher on its own COBOL and Fortran coding evals, though production use still needs expert review.

doubleAI Opens Early Access to Maxwell, AI That Rewrites Running Code

doubleAI opened early access to Maxwell, a Code Execution Model that rewrites binaries as programs run. Speed-ups are company claims.

MiniMax Rolls Out M3.1 Flash, a Faster, Cheaper Agentic Model

MiniMax’s M3.1 Flash targets agentic tasks with claimed near-3x speed and 70% lower cost. API now; weights later. Benchmarks are MiniMax’s own.

Quick Guide: Ask a Grok Bot to Read Your Usage CSV and Suggest Savings

User tip via @tejas3732: export Cursor usage CSV, ask your main Grok Bot where usage goes. His 10-15% claim; check the file before sharing.

OpenCode Console Breach Ran Up Charges on Users’ AI Accounts

OpenCode Console users report unauthorised AI charges after a breach. Anthropic and Google blocked keys, OpenAI is refunding, and the incident is ongoing.

DeepSeek Releases DeepSeek-V4.1-Flash-1017 Open-Weight Update

DeepSeek’s V4.1-Flash-1017 is a minor open-weight update. Its own table lifts many agent scores vs prior Flash; Opus 5 still leads HLE and Terminal-Bench.

How the Claude Code Team Reviews Code as Agent Output Surges

Anthropic’s Claude Code team: merged PRs more than doubled June–Sept while reverts fell over 40%. Most reading moved to machines.

Latest on TSN

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