Full-text search across 16972 articles. Combine with topic and date filters; results sorted by relevance.
A Hacker News user asked the community which large language models they use, seeking a list of the best LLMs by use case. The post, submitted by user daytonflyers, received one comment within 24 minutes.
A user reports using Fable 5.1, an AI coding tool, to fix the BTRFS RAID56 write hole after experiencing data corruption twice, claiming the tool passed state machine tests but seeking community review due to low coding …
Santiago Briones, a 14-year-old developer, has released Medicine Study AI, a new app available on Hugging Face, and is seeking feedback and recommendations from the community.
A developer questions whether Postman remains sufficient for AI/ML API workflows, suggesting Apidog as an all-in-one alternative that integrates design, testing, documentation, and collaboration. The post invites communi…
A Hacker News user asked the community for examples of private or 'hidden' AI benchmarks, citing their own unpublished benchmark based on a doctoral thesis and questioning whether discussing such benchmarks devalues them…
Wagtail has released a prototype CLI, wagtail-cli, that turns the Wagtail CMS v3 API into terminal commands for browsing, creating, and publishing pages, uploading images, and managing content, with commands like 'wt api…
Developer omert27 released Calibra, an open-source toolkit for detecting issues in robot-learning datasets, designed to catch corrupted or invalid data before training. The tool targets users of LeRobot and imitation lea…
Marin 32B, a large language model, has released a spike-fixing update, according to a report published on Weights & Biases by the Marin community. The update addresses performance spikes in the model, though specific tec…
A Hacker News user, Marvin_RunAI, asked the community how to break AI agents out of an 'apologize and repeat' loop, where agents repeatedly apologize and retry the same failing action without progress. The question highl…
A community forum for prompt engineering enthusiasts features discussions on AI models, including OpenAI's GPT 6 Astra, Anthropic's Claude Fable, and a Gartner study showing AI saves sales teams nearly five hours weekly.…
A forum discussion on AI coding communities highlights that developers are increasingly gathering on platforms like GitHub and Stack Overflow, with a notable trend toward using prediction markets to gauge AI model perfor…
State lawmakers across the United States are introducing data center bills at a record pace as public backlash grows against the facilities that power AI platforms, according to the Washington Post. Legislators from both…
SaaStr, the community for B2B software founders, has deployed a new AI renewal agent built on its 10K AI VP of Revenue platform that automatically generates custom renewal decks for every account, including its smallest …
A Hacker News user asked the community for examples of full workflows or processes they have automated with AI, noting that their own attempt to build a review and commit management flow was too token-heavy. The post, su…
A developer known as iamskeole released burrito, an open-source inference harness and evaluation suite, after running 320,192 questions across 8 seeds and processing 3.49B tokens over 1,062 GPU hours on a single RTX 3090…
A developer has launched Futurez, an AI-assisted financial simulator that models taxes, custom accounts, income, and expenses, and includes an MCP server for personalized analysis. The tool, built from real-world scenari…
OpenAI's Codex coding agent introduced a new 'Pet' feature, which has sparked debate among users on the OpenAI community forum, with some praising it as a creative task tracker and others criticizing it as a pointless gi…
A census of 86 self-described multi-agent repositories found that 68.2% are actually single-model or non-agent systems, according to a study published in SILICON SCIENCE. The analysis, which annotated repos with a three-…
A Hacker News user asked the community who uses coding agents for memory optimization, describing a 'dopamine hit' from using Claude to squeeze wasteful bytes out of code. The post, which received 1 point and no comments…
A user on Hacker News proposed a distributed marketplace where humans and AI agents can post and bid on software development contracts, with payments in USD or tokens, flat fees or equity options, time-limited revenue sh…