A compact digest of model releases, papers, agentic systems, coding automation, infra, security, and high-signal developer discourse. Feed candidates are ranked locally; the scheduled Hermes worker can add qualitative synthesis.
Hey HN, Anders and Tom here. We're building Magnitude, an inference engine for agents that optimizes itself to run as fast as possible on your hardware. It works on Mac, Linux, and Windows on any hardware and is up to 2x faster than llama.cpp. We're both software engineers and previously built an open source browser agent to 4k+ GH stars and 100k+ downloa…
On Friday I gave the closing keynote at the WeAreDevelopers World Congress North America in San Jose. I tied together the key trends from the past year into a chronological exploration of everything that happened in 2026. The video is on YouTube ; here are my annotated slides and notes to accompany the talk. And as an annotated presentation : # I'm going…
See also: Gemini 4 Argon (High): Intelligence, Performance and Price Analysis - https://news.ycombinator.com/item?id=49914236 Comments URL: https://news.ycombinator.com/item?id=49913571 Points: 770 # Comments: 509
I made this for kids around 10 to 14. A robot called Errol solves a math problem step by step and one of the steps is wrong. The kid has to find it and say what's wrong with it. Sometimes nothing is wrong, so just saying "there's a mistake" every time doesn't work. The user needs to enter an explanation if she finds an error to gain more XP; speed matters…
Article URL: https://turkeyland.net/thoughts/ai.php Comments URL: https://news.ycombinator.com/item?id=49913458 Points: 55 # Comments: 35
Article URL: https://www.ycombinator.com/companies/bild-ai/jobs/dAbC3Gd-founding-product-engineer Comments URL: https://news.ycombinator.com/item?id=49911531 Points: 0 # Comments: 0
Hi everyone, Sanjeev here- founder. My journey in AI started with wanting to break into emerging AI companies, but without deep hands-on experience, it was hard to even get noticed. I started with scope focused minor projects but then curiosity got expanded to understand what happens under the hood of LLM calls, what goes in & how reliable AI agents works…
Hello HN, I'm Ajo and I built Strata. I spent 4 years at Netflix solving self service for non-technical business users. I think I cracked it with my unique approach to semantic layer design. The key challenge is balancing expressiveness with ease of use for our non technical colleagues. It just so happens that focus made it work pretty well with LLMs too.…
Article URL: https://github.com/FredXing1/FinTrace Comments URL: https://news.ycombinator.com/item?id=49907790 Points: 3 # Comments: 0
Article URL: https://github.com/anis-marrouchi/agentx Comments URL: https://news.ycombinator.com/item?id=49908434 Points: 1 # Comments: 0
As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce agentic meta-reasoning, an inference-time harness that makes these choices an explicit and structured reasoning process. Workers carry out the task-level computation,…
Article URL: https://github.com/ucsandman/SideTap Comments URL: https://news.ycombinator.com/item?id=49912306 Points: 1 # Comments: 0
Article URL: https://www.growth.engineer Comments URL: https://news.ycombinator.com/item?id=49915329 Points: 1 # Comments: 1
Article URL: https://apartmamatevz.si/journal/posts/2026-09-30-cm-ai-docking-port-teaching-ai-agents-to-knock-on-the-right-door.html Comments URL: https://news.ycombinator.com/item?id=49914346 Points: 1 # Comments: 0
I had this idea that I wanted to make a small toy type game for AI to do that a human would not be able to play with. That's definitely not this but it turned a bit more "artistic", ofc you could just do the challenge manually (or assisted) and you can "tag" the wall too, but why? just let the computer do it. Comments URL: https://news.ycombinator.com/ite…
Article URL: https://incident-arena.com/ Comments URL: https://news.ycombinator.com/item?id=49913915 Points: 1 # Comments: 2
Article URL: https://fsdatalab.github.io/blog/introducing-quail/ Comments URL: https://news.ycombinator.com/item?id=49912536 Points: 3 # Comments: 0
Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two complementary dime…