Full-text search across 8183 articles. Combine with topic and date filters; results sorted by relevance.
Dupflo released Decision Ledger, an experimental set of three agent skills for Claude Code that records developers' architectural decisions and tracks how many they could defend in review, with the tool itself publicly s…
At the Raise Summit in Paris, Richard Kirby, Office of the CTO at 1Password, discussed the company's shift toward passkeys and AI credential management, noting that passwords remain prevalent but the focus is moving to m…
Anthropic's Claude Code now offers native voice dictation via the /voice command, which recognizes coding terms and supports project or branch names as transcription hints, though it requires a Claude.ai login and does n…
Yardmaster, a macOS terminal for managing multiple Claude Code sessions, launched with features including a sessions sidebar, waiting-on-you inbox, worktree sessions, and session persistence. The app, available via curl …
Elon Musk's SpaceX and Mark Zuckerberg's Meta released AI models this week that close the gap on OpenAI and Anthropic, with Grok 4.6 scoring nearly even with GPT-5.6 Sol Max on the Artificial Analysis Intelligence Index …
MetaMask launched its Agent Wallet, a self-custodial wallet designed for AI agents to execute onchain actions within user-defined rules, featuring spend limits, allowlists, and security checks. Ethereum core developers d…
Pratyush Choudhury, co-founder of Activate AI, India's first VC fund dedicated exclusively to AI, consumes 300 to 500 million tokens a day and spends a few hundred to a few thousand dollars daily on frontier AI models to…
OpenAI shipped a production application with one million lines of code written entirely by AI agents, using a disciplined harness rather than a smarter model. The LangChain engineering team moved from 30th to 5th place o…
SpaceXAI released Grok 4.6 on August 12, 2026, matching GPT-5.6 Sol with a score of 61 on the Artificial Analysis Intelligence Index, but the model trails competitors on coding benchmarks, recording 26% on Terminal-Bench…
Roborev, a new open-source tool, provides continuous code review for AI coding agents by automatically reviewing every commit and feeding findings back to the agent, enabling a hands-off write-review-fix loop. The tool, …
DeepSeek is recruiting researchers, engineers, and product staff for an Agent Harness team in Beijing and Hangzhou, according to its hiring page and reports from May 20–21, 2026. The roles focus on context management, me…
Zed CEO Nathan Sobo launched Delta on August 12th, opening a private beta for a multiplayer application that keeps agent conversations, code changes, and review comments in one synchronized workspace. Delta runs on Delta…
A community hackathon reproducing 2,200 papers from ICML 2026 found that 51% (1,103) had at least one claim independently verified, while 23% (496) had at least one claim falsified or contested, according to the ICML 202…
Anthropic's unreleased Claude research model improved a key bound on the Riemann Hypothesis from 41.6 to 67.2, surpassing the best prior human result, according to Anthropic. The model, guided by non-mathematician staffe…
DeepSeek V4 Pro, the 0813 release from DeepSeek, costs 43 cents per million input tokens and 87 cents per million output tokens via API, making it roughly 57 times cheaper than Gemini 3 Pro's $10.50 per million tokens. I…
A new analysis from Base44 identifies four sources of free AI coding credits in 2026—provider trial balances, student or startup programs, vendor free tiers, and ad-funded grants—and warns that only recurring grants are …
Veriframe, an OpenAI-compatible HTTP server written in Jolt, a Clojure dialect on Chez Scheme, wraps large language models in a verification harness that refuses to return answers until every claim is confirmed by formal…
Marmot, a data catalog platform, released a free OpenMetadata plugin that imports an entire OpenMetadata instance in about five minutes, including tables, topics, dashboards, pipelines, ML models, glossary, and lineage, …
A new comparison of eight open-source agent workspace tools — cmux, Superset, Orca, Paseo, Herdr, T3 Code, Goose, and Warp — finds they split into three distinct categories: agent workspaces, terminal runtimes, and agent…
Claude Code skills are reusable prompts that guide coding agents through specific development steps, and a new guide details how to install a skill library for a full dev workflow. The workflow splits into an outer loop …