Full-text search across 66194 articles. Combine with topic and date filters; results sorted by relevance.
Opus 5 achieved a 24% strict pass rate on a subset of the SlopCodeBench coding benchmark from UW Madison, only marginally higher than Opus 4.6's 17% in the original paper, and wrote five times more functions than Opus 4.…
Static MCP, a new open-source project, lets developers publish MCP tools as static, hash-verified files executed sandboxed on demand, eliminating the need for server infrastructure. The reference implementation, mcpwasm,…
OpenAI launched ChatGPT Work Mode, a dedicated environment within ChatGPT for Pro and Team subscribers that merges its Codex coding agent, Atlas memory system, and direct integrations with Gmail, Slack, Google Drive, and…
AI programming agents like Claude Code, Cursor, and Windsurf run on an AgentLoop analogous to a CPU's fetch-decode-execute cycle, but running them locally on laptops causes severe compute bottlenecks and session instabil…
Claude Opus 4.8 successfully translated 31 of 33 pandas scripts to idiomatic Polars code in one-shot tests, enabling faster data pipelines on cheaper hardware. The translations ran correctly and output matched, though tw…
Kog released Laneformer 2B, a 2.3B-parameter coding model designed for high-speed decoding, on Hugging Face Hub. The model was trained from scratch with latency as the primary objective, achieving 45.1% HumanEval+ and 51…
A senior developer with over a decade of experience argues that the most valuable skill in AI-assisted software development is knowing when not to use AI. The developer warns that AI-generated code can introduce hidden r…
Anthropic's Claude Fable 5 model, when paired with the Cursor agent harness, achieved 72.6% FuncPass and 29% SecPass on 200 real-world vulnerability-fixing tasks, topping the fair leaderboard. The same model under Claude…
A software engineer shares 10 AI habits that would have saved months of wasted effort, emphasizing that engineers who use AI effectively will replace those who don't. The post cites a 340% increase in job postings requir…
PingCAP's research team introduced TINE, a system that binds every AI agent iteration to a Git commit, a TiDB branch, and a sandbox runtime to solve schema drift, irreproducible state, and rollback gaps in agentic app bu…
Developers demonstrated multi-agent AI collaboration using Git as a shared message bus for Claude Code and Codex, while AI gateways matured into a standard architectural concern for cost control and observability. OpenAI…
Anthropic published a candid post-mortem on two years of deploying Claude as an autonomous agent, detailing security challenges and containment strategies, while also announcing a partnership with KPMG to deploy Claude t…
GitHub is piloting an experimental general-purpose accessibility agent that has reviewed 3,535 pull requests with a 68% resolution rate, automatically catching and remediating accessibility issues before they reach produ…
Developers seeking alternatives to Windsurf in 2026 are primarily motivated by pricing predictability, local-first workflows, and access to real agent engines like Claude Code or Codex. Nimbalyst leads as the top alterna…
A developer released safe-grokbot-bridge, an open-source daemon that gives a remote AI agent such as xAI's Grok Bot an authenticated HTTP API to a user's machine, limited to chosen folders and to driving Claude Code, Cod…
OpenAI released GPT-6.1 Terra on October 26, 2026, joining Anthropic's Claude Opus 5.5 and Google's Gemini 4 Argon as the three flagship models teams are comparing, with no single model winning every test. The one indepe…
A developer has published a reproducible bake-off method for comparing Meta's Muse Wonder against Claude Opus 5.5 on a user's own repository, after noting that Meta's model card claims Wonder leads on long-horizon coding…
Kerneta's .Cai plain-text code graph answers a module-import query in 22 tokens versus Graphify's 4,696 — 218x fewer — and 64,075 tokens for reading httpx's own source, or 2,976x fewer, according to the Show HN post. On …
Pydantic released a hosted Logfire MCP server that exposes OpenTelemetry traces, logs, and metrics to any Model Context Protocol client, running at https://logfire-us.pydantic.dev/mcp for US projects and https://logfire-…
Anthropic released Claude Opus 5.5, the first model in its new Claude 5.5 family, which the company says performs at the level of Claude Fable 5.1 on most work while costing 40% less to run than Opus 5. The model is pric…