Six questions before you add an LLM
Article URL: https://cameronmpalmer.medium.com/should-you-even-use-an-llm-b4f3b7914f4d Comments URL: https://news.ycombinator.com/item?id=49008624 Points: 3 # Comments: 1
Latest
Got these baddies in the mail today (2X 3080 20GB)
About to plug them in. Currently running a single 3090. I got these for less than the price of a single 3090. 24GB wasn't enough for…
Can a MUD evaluate LLMs? A $99 proof of concept
I'm the author of a paper my friends and I wrote after we were curious if a MUD, text games originating in the 1970s, could be…
RT Thomas Wolf: I don’t believe reality is a simulation, but you genuinely couldn’t script this timeline: • Two weeks ago: At @swyx’s AI Engineer …
RT Thomas WolfI don’t believe reality is a simulation, but you genuinely couldn’t script this timeline:• Two weeks ago: At @swyx’s AI Engineer World’s Fair in…
A Zipper Patent Sat in a Garage for 40 Years. Now It's Real
Article URL: https://www.yankodesign.com/2026/05/31/a-zipper-patent-sat-in-a-garage-for-40-years-now-its-real/ Comments URL: https://news.ycombinator.com/item?id=49008512 Points: 7 # Comments: 0
How do neural networks regress cubic polynomials? Apparently, they use a trick invented in Milan 500 years ago
TL;DR: Neural networks can easily learn to regress cubic polynomials of type mjx-container[jax="CHTML"] { line-height: 0; } mjx-container [space="1"] { margin-left: .111em; } mjx-container [space="2"] {…
Making
Article URL: https://beej.us/blog/data/ai-making/ Comments URL: https://news.ycombinator.com/item?id=49008440 Points: 4 # Comments: 0
Models don’t seem to be dishonest in the way humans are
TLDRModels often behave dishonestly without acquiring a coherent deceptive disposition.We trained some mid-sized models on their own plausible but false reasoning.True and false training usually produced…
Show HN: HN Hall of Fame – browse 3,100 legendary Hacker News links
Article URL: https://www.orangecrumbs.com/hall/ Comments URL: https://news.ycombinator.com/item?id=49008406 Points: 6 # Comments: 2
The quiet beat before a dragon takes off, when the whole film is still holding its breath. By Jason Chalkley. Made with Luma.
The quiet beat before a dragon takes off, when the whole film is still holding its breath. By Jason Chalkley. Made with Luma.
Critical Minerals: Reducing U.S. Import Reliance with Substitution and Recycling
Article URL: https://www.gao.gov/products/gao-26-108687 Comments URL: https://news.ycombinator.com/item?id=49008346 Points: 4 # Comments: 0
Why I Am Not Going to Buy a Computer
Article URL: https://karlvmuller.com/posts/why-i-am-not-going-to-buy-a-computer/ Comments URL: https://news.ycombinator.com/item?id=49008276 Points: 30 # Comments: 9
I Am Buiding BorgIOS to de-shitify the Internet
Article URL: https://github.com/bitmonky/BorgIOS Comments URL: https://news.ycombinator.com/item?id=49008217 Points: 3 # Comments: 0
Show HN: Bento – An entire PowerPoint in one HTML file (edit+view+data+collab)
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a…
Neo Radar: A browser-based orbital mechanics engine with 41k real asteroids
Article URL: https://neoradar.space Comments URL: https://news.ycombinator.com/item?id=49008143 Points: 3 # Comments: 0
OpenAI Presence
Article URL: https://openai.com/index/introducing-openai-presence/ Comments URL: https://news.ycombinator.com/item?id=49008089 Points: 24 # Comments: 0
Though I would suspect that models like Kimi K3 & GLM-5.2 would also qualify, this is the first time that an open model has reported gold-medal level …
Though I would suspect that models like Kimi K3 & GLM-5.2 would also qualify, this is the first time that an open model has reported gold-medal…
UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching
（＊日本語は英文の後に） Can test-time scaling work for diffusion language models? In our ICML 2026 paper “UnMaskFork,” we show that having multiple masked diffusion language models collaborate on…
Kling MCP Tutorial: Create Cinematic AI Performances in Minutes Learn how to use Kling MCP to build a complete creative workflow in your favourite age…
Kling MCP Tutorial: Create Cinematic AI Performances in MinutesLearn how to use Kling MCP to build a complete creative workflow in your favourite agent — from…
Perlin's Noise Algorithm
Article URL: https://blog.jaysmito.dev/blog/02-perlins-noise-algorithm/ Comments URL: https://news.ycombinator.com/item?id=49007863 Points: 5 # Comments: 0
Comment on Measuring Reward-Seeking by Instilling Contrastive Beliefs paper
This is interesting research! https://alignment.openai.com/measuring-reward-seekingIt made me think of few overlapping hypotheses for what might be happening here, how did the grader behavior emerge at the…
The Pillars of an API Platform
Article URL: https://launchany.com/the-pillars-of-an-api-platform/ Comments URL: https://news.ycombinator.com/item?id=49007839 Points: 4 # Comments: 0
Airbus Full Scale Foldable Wing Extensions
Article URL: https://www.airbus.com/en/newsroom/press-releases/2026-07-airbus-launches-new-flight-test-programme-for-wing-of-tomorrow Comments URL: https://news.ycombinator.com/item?id=49007831 Points: 3 # Comments: 0
An issue with Codex and Claude Code is that users need more control over the particular configurations of subagents that orchestrator AIs use. I want …
An issue with Codex and Claude Code is that users need more control over the particular configurations of subagents that orchestrator AIs use.I want to decide…