Full-text search across 9587 articles. Combine with topic and date filters; results sorted by relevance.
The AI engineering community has adopted the term 'loop' to describe at least four distinct architectures: execution loops for agent decision-making, task loops that restart agents until tests pass, product loops for cod…
Scarf, a cash-flow-positive software company, is moving away from Haskell after seven years of production use, citing slow feedback loops and development costs. The company will retain Haskell for its performance-critica…
A user on Hacker News is seeking scent ideas for a candle that would smell like burned LLM tokens, as a birthday gift for a data engineer relative. Suggestions from the community include burned toast, diesel fuel, and ra…
A Hacker News user asks the community for opinions on using multiple MCP (Model Context Protocol) native tools without a frontend, and inquires about the token cost of running several MCPs simultaneously.
A Hacker News user asks the community about practical local LLM usage, seeking real-world experiences with models, hardware, use cases, and trade-offs versus APIs.
A coordinated movement against AI data centres is rising across Canada, with local groups already securing victories in opposing new developments. The resistance targets the environmental and community impacts of the dat…
A developer successfully ran GLM 5.2, a 744B-parameter Mixture-of-Experts model, on a laptop with 32GB RAM by streaming routed experts from disk. The project, called Colibrì, is a single C file engine that activates only…
A developer is considering building a service that lets readers pay $15 per book to discuss it with an official AI clone of its author, trained on the author's works and interviews, with revenue shared with the author. T…
A Hacker News user asks the community for patterns or structures to manage long-lived research or non-coding projects using large language models, citing their own project collecting nut-free restaurants in Chicago as an…
A Hugging Face forum user deleted a topic about running local LLMs on Android. The forum shows related discussions on Android LLM apps and models, indicating ongoing community interest in on-device AI.
A bloody bear attack in Mammoth Lakes, California, where a couple and their dogs fought a young bear, killing it, has reignited tensions between humans and wildlife. The incident has divided the community, with some blam…
A software engineer who uses LLMs daily argues against fears of AI-induced deskilling, reporting that an honest audit of their own habits found no erosion of core skills despite widespread anxiety in the tech community.
The Godot Foundation updated its contribution policy to ban autonomous AI agent use and AI-generated code, citing a surge in low-quality AI contributions that overwhelm reviewers and demoralize the community. The new rul…
A Hacker News user asks the community for advice on moving from cloud-based AI services to private models for sensitive data analysis and reasoning, considering options like adding dual RTX 5090 GPUs or leasing compute.
Anthropic may release Claude Sonnet 5 later today, but it might not outperform Opus 4.8, according to unconfirmed reports. The news has sparked discussion in the AI community about the relative capabilities of the models…
A developer is building agent-qa, a self-improving QA agent for software teams that has processed over 500 million tokens and thousands of test runs, and is seeking community feedback on AI agent usage for testing featur…
A Hugging Face forum user asked which open-source large language model the community prefers for chatbot development and why, sparking discussion on model selection criteria.
A developer building a worklog automation tool for coding agents asks the HN community for the best local language model under 3 billion parameters to process screen captures and update project management tools.
GemCities launches free hosting for Gemini protocol capsules, allowing users to publish content at username.gemcities.com without server knowledge. The service offers 50 MB storage, no ads or tracking, and includes a Gem…
A developer asks the Hacker News community for best practices on managing pull request reviews, citing options such as agent-based review, plan review, critical path review, and reliance on integration or manual testing.