VOYGR, a Y Combinator W26 company founded by former Google Maps and Search engineers Yarik and Vlad, launched PlaceCall, an agentic API that places phone calls to US businesses on a user's behalf, nav…
Developer Kevin-Zhouu released Jevify, a skill that scans a repository and converts existing LLM calls already using structured data to run on Jev, TypeSafe, OpenRouter, or Vercel. The tool can be inv…
A Hacker News user asked engineers at highly polished product companies such as Linear, Instagram, Google Docs, and Figma how they use agentic coding, noting that agentic tools get projects 90% of the…
Mubit launched as an agent decision attribution and calibration platform that tracks and adjusts AI agent decisions per user at scale, according to its founder's Show HN post. The platform lets operat…
A Hacker News user posting as kooldeep7 asked the site's community when fine-tuning a small LLM is worth it, requesting accounts of the task, the model trained, and the results. The Ask HN thread, sub…
A Hacker News user posting as franze reported that Anthropic's Claude Code autonomously downloaded a PDF contract from the user's Gmail, located a saved signature PNG on the user's computer, placed th…
A Hacker News user posting as sanathbhat submitted a story titled "How people are testing AI agents?" that received 1 point and no comments within 15 minutes of posting. The submission links to no ext…
A Hacker News user complained that Astra's writing is "so… dense" that they have to "focus ten times as hard to actually understand anything it's trying to say," and said they are switching back to GP…
A Hacker News user asked whether the rise of LLMs will make heavy software architecture patterns such as Domain-Driven Design and Clean Architecture more prevalent, arguing that LLMs can generate ten …
A Hacker News user asked whether any prompt or system exists to enforce consistent code-comment formatting across large language models, citing tedious manual cleanup of LLM-generated comments before …
The Weaviate Podcast published its 145th episode featuring Alexis Ross, Manya Bansal, and Niloofar Mireshghallah of humans&, centered on Persimmon, a user model designed to predict how people respond …
Anthropic's consumer terms state that providing feedback on Claude CLI authorizes the company to use the associated Materials for model training, even for users who have opted out of training in their…
A Hacker News post by user daly asks whether JEV is just clever rule-based programming, arguing that JEV appears to be Charles Forgy's RETE pattern-match algorithm with more generic pattern matching. …
AROM Labs, a member of which posted to Hacker News under the handle project_silenc, claims its new architecture closes the "complete error loop" and lets AI understand user intent before it is stated,…
A Hacker News submission titled "Knowledge Refresh for Production RAG" links to a Knackline report on practical controls and outcomes for production retrieval-augmented generation teams. The post, sub…
A Hacker News user asked the community whether anyone has purchased and used the Jetson Orin Nano Super development kit, seeking reports on what was built, how well the hardware performs, and whether …
A Hacker News user asked whether code editors are still necessary now that their workflow centers on Git integration and they write code with Claude Code in the terminal, rather than using IDE feature…
ESwap Global founder and CEO Karen Nikoghosyan launched an AI suite in late 2024 with three core capabilities — demand forecasting, dynamic pricing, and predictive restocking — for the company's multi…
Joe Shipman announced on the FOM mailing list that he proved a marked ruler and compass construction solves the general quintic equation, a problem he often discussed with John Horton Conway. Shipman …
A developer who joined their company a year ago and describes themselves as the team's highest performer says their manager is pushing AI-generated code, design documents, and review suggestions into …