We run scheduled news sweeps and publish only the items that clear the editorial threshold.
Modern Web Guidance is a set of agent skills and a local CLI. The agent searches about 200 hand-written guides on current HTML, CSS and browser APIs and loads the matching guide into its context.
AWS made Nitro Sandboxes available. They are lightweight VMs managed by the Nitro Hypervisor, and each EKS pod, ECS task or VM that uses one gets its own hardware isolation boundary on a shared EC2 instance.
Andrews and Zhang pointed Opus 5.5 at CPython 3.15.2 and had agents copy its functions into Lean line by line. Each function goes through four steps: copy the source, test the copy against real Python on at least 50,000 inputs, prove or…
DeepMind describes AlphaProof Code as a multi-LLM agentic framework in which human experts and AI decide what to prove and a group of agents does the proving. Its researchers worked with models to turn Signal's security goals into formal…
Meta lists muse-ember-1.0 at $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 200K tokens, with a 1M-token context window and up to 512K output tokens. Meta says it matches Claude Haiku 5.5's best…
Two Amazon engineers swapped Claude Sonnet 4.6 for Strands Decider, a model that returns a probability for each option in a fixed list instead of generating text, on an internal ticketing system with 20 label categories. They report average…
Panasenko, who built the Mitts build tool, reports that a parallel build of 12 rustls worktrees on Linux x86_64 took 3 min 42 s with plain Cargo and 9.3 s with Mitts. Cargo with a warm sccache took 3 min 59 s.
Little's executive summary argues that AI has made writing code cheap but has not made deciding whether it is right cheaper, and that human review under real volume becomes either a bottleneck or a rubber stamp. His answer is a factory of…
Anthropic describes what it calls a toy experiment in which 1,000 agents running an early version of Fable 5.2 reproduced a formal proof of Fermat's Last Theorem. The team took 28.7 hours, used one-third as many output tokens and wrote a…
The repository holds Opus 5.5 and a set of 20 public multi-user tasks fixed and changes only the harness. On Opus 5.5, pass rates were QM 72.5%, Claude Code 76.3%, Hermes Agent 78.8% and OpenClaw 76.3%, and no tested pair could be told…
An OpenAI-published interview with CodeRabbit CEO Harjot Gill, who says the company has shipped roughly 20 times more software over six months with the same team using Codex. He says the first bottleneck after adopting coding agents is code…
Anthropic says Fable 5.2 and Mythos 5.2 are the same underlying model. Fable carries cyber and biology safeguards and is available to everyone as claude-fable-5-2; Mythos is open by application through Anthropic's verification programs.
Epic describes the release as "the first Unreal Engine release built primarily with agentic workflows." Per the announcement, a handful of people directed fleets of agents to port AI tooling from the UE6 development branch and to add the…
Kurtzer's report describes what he calls Human-Directed Agentic Engineering. The human defines architecture, constraints, milestones, acceptance criteria and stopping points.
The leaderboard runs nine harnesses on three open-weight models (GLM-5.3-Flash, DeepSeek-V4.1-Flash and Flint) across Terminal-Bench 2.1 and DeepSWE v1.1. Each harness gets the same model, provider and reasoning effort, three attempts per…
GitHub says you can now keep "AI agent skills, prompts, and instructions" up to date with Dependabot version updates for Agent Package Manager (APM). Dependabot opens pull requests to update supported git dependencies declared in apm.yml…
GitHub Next's open source project lets you write automation in Markdown for tasks such as issue triage, CI failure analysis, documentation updates and test writing, using Copilot or another coding agent inside GitHub Actions. The Markdown…
Starting December 2, 2026, GitHub Actions will block pull_request_target events by default in all public repositories unless an Actions event policy explicitly allows them. Enforcement was previously scheduled for November 2.
Under the theme "Putting more agents to work," the board describes developers running several agent sessions in parallel and steering each one, and handing agents larger jobs such as unattended overnight builds that developers review…
Thoughtworks blog, November 4, 2026 · Argues that a self-improving harness needs an evaluation harness, provenance for self-authored changes and a rollback path, and says to "automate the proposal and keep the approval." An opinion piece…