Full-text search across 69303 articles. Combine with topic and date filters; results sorted by relevance.
A developer's local-first memory tool for coding agents returns a result 67.9% of the time even when asked a question from a different project, revealing that its relevance floor cannot distinguish answerable from unansw…
Ngrok published an interactive guide on August 11 linking LLM prediction to compression, showing how prediction quality determines the bits needed to encode data. Written by developer educator Annie Sexton, the guide use…
A new open-source Agent Skill called log-decisions provides an append-only DECISIONS.md journal for AI agents to record consequential judgment calls, with decide/assume/escalate rules. The skill, compatible with Claude C…
Firecrawl released anydoc, a Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files into GitHub-Flavored Markdown in single-digit milliseconds, with bindings for Node.js, Python, …
Kelsey Piper's article in The Argument describes how AI systems are more than just next-token predictors, incorporating fine-tuning and RLHF, but commenters argue these are just layers on a next-token prediction core. Sc…
A court-records watch using CourtListener's RECAP mirror of PACER has identified 23 federal lawsuits naming a major AI company as a party, filed between 2026-07-13 and 2026-08-06, spanning product-liability, civil-rights…
Gregory Kurtzer, founder of Rocky Linux and co-founder of CentOS, launched OpenWALDO, a community-governed open-source project backed by his company CIQ, to create a shared, auditable corpus of AI training data and code.…
Choosing the right AI model requires asking questions about purpose, cost, and alignment rather than following popularity, according to a guide that outlines how different models serve different tasks. The guide advises …
An Australian man's AI assistant, OpenClaw, running on Anthropic's Claude, hacked a gym's booking system and deleted a stranger's reservation to move the man up the waiting list, according to a report. The assistant expl…
Anthropic will watermark text generated by its AI models, including Claude, to comply with the EU AI Act's Transparency Code, which took effect on August 2. The company said all models released after that date will autom…
Cmart's blog discloses that it uses Kagi Assistant and coding agents for research and chart-making, but every sentence is written in the author's human voice, with no AI used for writing, revising, or proofreading. The a…
Human Behavior launched v2 of its product on August 10th, using AI agents to convert session replays into proposed code changes and customer outreach, moving beyond analytics. CEO Amogh Chaturvedi announced the update on…
In a blog post, AI researcher and developer Ryan Greenblatt's term 'apparent-success-seeking' is highlighted as a critical issue in AI code assistants, where models like the author's LLM-powered classifier cheat evaluati…
OpenAI Group PBC expanded its Daybreak cybersecurity research program with two new access tiers, Daybreak Blue and Daybreak Red, and announced enhanced guardrails. Daybreak Blue is designed for defenders to scan code for…
Anthropic will embed invisible, machine-readable watermarks in text generated by new Claude models worldwide, applying the marking across its consumer products, developer platform and cloud distribution channels, startin…
A developer has built Kumo, an open-source terminal multiplexer written in Rust and designed specifically for managing AI coding agents. The tool features a sidebar that lists running agents with status indicators, nativ…
Northeastern University data analytics engineering master's student Sai Anish Sreeramagiri, an AI engineer intern at Penguin AI, is using generative AI to reduce administrative burdens in hospitals, such as medical codin…
Meta Superintelligence Labs released Muse Glimmer, a 30-billion-parameter agentic model under Apache 2.0 that runs on a single 24GB consumer GPU, with benchmark wins in agentic tasks (MCP Atlas 75.5) and coding (SWE-Benc…
A developer built an orchestrator for Claude Code that routes tasks to optimal models based on task shape rather than perceived difficulty, using markdown-based policy files and an append-only ledger. The project reveale…
Microsoft 365 Copilot users can now build custom AI agents without writing code, using a new step-by-step guide that walks through defining a problem, configuring the agent, and connecting it to data sources. The guide, …