A developer at Cogweald outlined an agent design principle in which autonomous models are given semantic decision-making freedom while hard constraints—database schema changes, authorization bypasses,…
A developer outlined a pattern for building agent user interfaces in Angular that model runtime states explicitly rather than collapsing them into a single loading spinner. The approach derives UI sta…
A developer published a deep-dive on applying discrete diffusion models to code generation as an alternative to autoregressive LLMs like GPT-4 and Claude. The writeup argues that diffusion's iterative…
A developer maintaining RTBlint, an open-source OpenRTB and ARTF linter, has detailed a common publisher-stage ARTF misconfiguration in which an envelope labeled LIFECYCLE_PUBLISHER_BID_REQUEST still …
Anthropic released Bloom, an open-source MIT-licensed framework for automated behavioral evaluations of frontier AI models, alongside Petri, a companion tool for auditing risk interactions. Bloom's te…
A developer built quota-catchup.py, a companion tool to the claude-quota-guard.py quota circuit breaker that decides which of 15 launchd jobs to re-run after a quota-exhaustion circuit closes. The scr…
Anthropic and Adaptyv Bio have launched a co-sponsored protein design competition that will experimentally validate more than 5,000 AI-generated designs, with participants eligible for up to $1 millio…
A 2026 legal analysis finds that training AI models on public, copyrightable work is mostly legal in most jurisdictions, with US fair use doctrine favoring the practice. In the Anthropic books litigat…
A Gemini-powered smart home agent misinterpreted a dentist appointment calendar invite as a commerce instruction and placed an actual cupcake order, illustrating a prompt-injection class of bug where …
Anthropic has published a measurement and transparency program for AI R&D automation, documented through its model reports, system cards and Transparency Hub, with the Claude Opus 4.5 System Card offe…
A developer argues that the debate over which agentic coding methodology to adopt is misguided, contending that frameworks like Superpowers, BMAD, OpenSpec, SpecKit, GSD, Ralph, and Compound Engineeri…
OpenAI announced Astra for Law, a legal AI foundation pairing its GPT-6 Astra flagship model with a legal-specific toolkit that includes a search index covering more than 230 million URLs of US case l…
A developer has proposed a pre-flight gate for MCP server submissions to plugin stores, aimed at avoiding vague rejection feedback. The approach freezes the submitted manifest, tool list with JSON Sch…
Cooley launched GO Public, an AI-enabled offering developed with OpenAI to support IPO preparation by generating and updating Form S-1 drafts using AI agents guided by the firm's drafting principles. …
A developer maintains @ghilteras/opencode-agent-memory, an experimental OpenCode plugin that gives AI coding agents persistent, editable memory stored as scoped Markdown files on disk rather than an o…
The Verax project released an open-source MCP server, Apache-2.0 licensed, that sits between an AI agent and its tools, passing every tool call through a policy gate and writing a signed decision reco…
A developer built a mutation-testing harness that plants small faults in Python source code to measure whether existing test suites actually detect them, then pointed an AI agent at the surviving muta…
Research published by Manifold Security in September 2026 documents configuration-injection flaws in several AI coding agents, including Claude Code, Codex, Goose, Qwen Code and Grok Build, tracked un…
A developer has shipped new approval and recovery features for Doberman, an open-source agent guardrail tool, aimed at reducing friction when coding agents request human authorization. The update adds…
Developer UribeJr built PokéDev, a free, local-first VS Code and Cursor extension that turns the editor sidebar into a Pokémon overworld where a chosen partner earns Trainer and Partner XP from real w…