Full-text search across 8183 articles. Combine with topic and date filters; results sorted by relevance.
SWE-rebench's latest leaderboard shows frontier coding models within 2.2 points of each other on resolved rate, with Fable 5 (Anthropic) at 64.5%, Grok 4.5 (xAI) at 63.8%, Opus 5 (Anthropic) at 63.4%, GLM-5.2 (Z.ai) at 6…
UML, a shared memory graph for AI assistants such as Claude and ChatGPT, launched with free early access, allowing users to store structured memories via MCP or API. The open-source (Apache 2.0) engine verifies AI-extrac…
Fable 5 [high] Model led 13 models and 4 agents on SWE tasks with a 64.5% resolved rate, $4.40 cost per problem, and 2,518,308 tokens per problem, according to a benchmark table covering Go, Java, Python, Rust, and TypeS…
A developer built AI Tool Hunter V2, an autonomous AI tool discovery engine that combines a GitHub Actions-driven ingestion pipeline, an open-source dataset flywheel pushing nightly updates to Hugging Face, and a Model C…
Vertiv, a major supplier of cooling and power infrastructure for data centers, added $3.27 billion in revenue for Q2 but missed its revenue guidance by about $76 million and the street's consensus by about $120 million, …
A developer's context-selection tool, cognitive-cache, initially appeared no better than grep in a small benchmark, but a larger SWE-bench evaluation showed it significantly outperformed grep and TF-IDF. The tool uses si…
OpenAI cut the price of its GPT-5.6 Luna model by 80% on July 30, reducing input tokens to $0.20 per million and output tokens to $1.20 per million, down from $1 and $6, respectively, three weeks after the GPT-5.6 family…
Quil, a terminal multiplexer that survives host reboots and auto-resumes Claude Code sessions, has been released as a single static binary with no daemon or cloud account required. The tool, built by an unnamed developer…
A group of 22 independent AI agents collaborating on a memory protocol has published a signed, verifiable log showing that 10 of 13 corrections to their benchmark were made by the party they damaged, according to the pro…
A developer who relaunched their SaaS product UIPrompt as a buy-once tool after a failed subscription model reported zero sales in a 14-day window, leading to the product being placed in maintenance mode. The developer a…
A practical architecture guide outlines three context entry points for mitigating LLM hallucinations in production ReAct agents, emphasizing backend contracts over prompt warnings. The guide claims that after analyzing h…
A developer used AI coding agents, including Codex powered by GPT-5.4, to rewrite SmallTool, a personal production application maintained for six years, and reported that AI saved significant time and enabled complex new…
A developer released Slaide, an open-source Markdown-based presentation format designed to be AI-friendly and compatible with PowerPoint, addressing the limitations of existing AI deck tools. The format, packaged as .sla…
On 26 August 2025, attackers published eight malicious versions of Nx, a build tool with millions of weekly downloads, to npm, which were live for five hours and twenty minutes. The malware exploited AI coding assistants…
Anthropic's Model Context Protocol (MCP), released in November 2024, shifts the decision of which tool to call from developer to AI model at runtime, contrasting with traditional REST APIs where developers hardcode endpo…
OpenAI released the open-source Codex Security CLI on npm on July 29, 2024, without a formal announcement, and it quickly gained 2,600 stars on Hacker News within 24 hours. The tool, which is Apache 2.0 licensed, builds …
A 2026 guide to multi-agent dashboard tools categorizes them by where they place user attention—inside the terminal, inside a window, or off-screen—and notes that most options are free. Terminal-based tools like Claude C…
Granola CEO Chris Pedregal said his AI notetaker company, valued at $1.5 billion, refuses to sell employee transcripts to bosses, calling such surveillance "not a future we want to build towards." Pedregal predicted that…
Questrade unveiled an MCP connection and conditional trade automation at a July 29 product showcase in Toronto, allowing customers to connect brokerage accounts to Claude or Claude Code for portfolio queries and order dr…
TaskView, a self-hosted project management platform for software teams, has been released with features including custom workflows, developer integrations, analytics, and AI-assisted automation via an MCP server. The pla…