DatBench: Discriminative, faithful, and efficient VLM evaluations
Article URL: https://arxiv.org/abs/2601.02316 Comments URL: https://news.ycombinator.com/item?id=46515648 Points: 4 # Comments: 0...
3dHacker NewsTechnologyImpact
Article URL: https://arxiv.org/abs/2601.02316 Comments URL: https://news.ycombinator.com/item?id=46515648 Points: 4 # Comments: 0...
I built an open source web app that generates cover letters using local AI models (Ollama, LM Studio, vLLM, etc.) so your resume and job application data never leaves your machine. No placeholders. No...
Article URL: http://www.observationalhazard.com/2025/12/c-java-java-llm.html Comments URL: https://news.ycombinator.com/item?id=46408510 Points: 4 # Comments: 0...
Article URL: https://embd.cc/llm-problems-observed-in-humans Comments URL: https://news.ycombinator.com/item?id=46527581 Points: 6 # Comments: 0...
Article URL: https://arxiv.org/abs/2512.02080 Comments URL: https://news.ycombinator.com/item?id=46411539 Points: 5 # Comments: 0...
Traceformer.io is a web application that ingests KiCad projects or Altium netlists along with relevant datasheets, enabling LLM-based schematic review. The system is designed to identify datasheet-dri...
Article URL: https://lethain.com/agents-coordinators/ Comments URL: https://news.ycombinator.com/item?id=46456682 Points: 3 # Comments: 0...
Article URL: https://github.com/mprajyothreddy/brainkernel Comments URL: https://news.ycombinator.com/item?id=46435142 Points: 5 # Comments: 4...
Raymond here from Butter.dev, an LLM response cache built as a chat-completions proxy. Today we're launching a key feature for the platform: the ability to generalize on dynamic, templated inputs. Cac...
Hi HN, I've been exploring various applications of formal methods to ML/interpretability and I've been hoping to get more eyes on the approach. I have been working on a small interpretability project ...
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized ...
Article URL: https://github.com/patrick48001/ThinkPad-Stream-Sentinel-VLC-Video-Source-reset-disable-stream-shutter Comments URL: https://news.ycombinator.com/item?id=46468411 Points: 4 # Comments: 1...
I thought it would be interesting to have ID style hover docs outside the IDE. Hover is a Chrome extension that gives you IDE style hover tooltips on any webpage: documentation sites, ChatGPT, Claude,...
AI pioneer Yann Lecun isn't sold on the "completely LLM-pilled" researchers that will lead Meta's AI development. Brian Snyder/Reuters; Fabrice Coffrini/Getty Images AI pioneer Yann LeCun pred...
An Uber logo is shown on a rideshare vehicle during a statewide day of action to demand that ride-hailing companies Uber and Lyft follow California law and grant drivers "basic employee rights'', ...
Nothing’s Ear (a) come in a bright yellow color, though you can also buy them in black and white. The new year has brought a wave of deals on wireless earbuds and headphones, from the fitness-focused ...
If you're familiar with the world of components, it's no secret that GPU prices have been all over the place for a while now, and that likely will only increase in 2026. Rumors of NVIDIA cutting back ...
Image and video capabilities could be crucial in 2026. Getty Images Partners a16z said ChatGPT is winning the consumer AI race, but things can change "very quickly." They predict that image an...
A RAM (random access memory) chip, commonly used in PCs. HUIZENG HU/Getty Images As AI companies snap up memory chips , smartphone and PC makers face higher costs and tighter supply. IDC projected a 2...
CEOs are using AI to research topics and summarize emails. Franco Origlia/Ethan Miller/Getty Images; Alexander Drago/via REUTERS CEOs are integrating AI into their personal and professional lives. Nvi...