LÖVE: 2D Game Framework for Lua
25 by cl3misch | 7 comments on Hacker News.
top story news
top story haker news new yourk tims
Ad
Sunday, 5 April 2026
New top story on Hacker News: Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code
Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code
9 by vbtechguy | 2 comments on Hacker News.
9 by vbtechguy | 2 comments on Hacker News.
Saturday, 4 April 2026
Friday, 3 April 2026
New top story on Hacker News: F-15E jet shot down over Iran
Thursday, 2 April 2026
Wednesday, 1 April 2026
New top story on Hacker News: The AI Marketing BS Index
Tuesday, 31 March 2026
New top story on Hacker News: Show HN: PhAIL – Real-robot benchmark for AI models
Show HN: PhAIL – Real-robot benchmark for AI models
7 by vertix | 7 comments on Hacker News.
I built this because I couldn't find honest numbers on how well VLA models [1] actually work on commercial tasks. I come from search ranking at Google where you measure everything, and in robotics nobody seemed to know. PhAIL runs four models (OpenPI/pi0.5, GR00T, ACT, SmolVLA) on bin-to-bin order picking – one of the most common warehouse operations. Same robot (Franka FR3), same objects, hundreds of blind runs. The operator doesn't know which model is running. Best model: 64 UPH. Human teleoperating the same robot: 330. Human by hand: 1,300+. Everything is public – every run with synced video and telemetry, the fine-tuning dataset, training scripts. The leaderboard is open for submissions. Happy to answer questions about methodology, the models, or what we observed. [1] Vision-Language-Action: https://ift.tt/Op5o1Im
7 by vertix | 7 comments on Hacker News.
I built this because I couldn't find honest numbers on how well VLA models [1] actually work on commercial tasks. I come from search ranking at Google where you measure everything, and in robotics nobody seemed to know. PhAIL runs four models (OpenPI/pi0.5, GR00T, ACT, SmolVLA) on bin-to-bin order picking – one of the most common warehouse operations. Same robot (Franka FR3), same objects, hundreds of blind runs. The operator doesn't know which model is running. Best model: 64 UPH. Human teleoperating the same robot: 330. Human by hand: 1,300+. Everything is public – every run with synced video and telemetry, the fine-tuning dataset, training scripts. The leaderboard is open for submissions. Happy to answer questions about methodology, the models, or what we observed. [1] Vision-Language-Action: https://ift.tt/Op5o1Im
Monday, 30 March 2026
New top story on Hacker News: Do your own writing
Sunday, 29 March 2026
New top story on Hacker News: Show HN: I made a "programming language" looking for feedback
Show HN: I made a "programming language" looking for feedback
3 by alonsovm | 2 comments on Hacker News.
3 by alonsovm | 2 comments on Hacker News.
Saturday, 28 March 2026
New top story on Hacker News: OpenCiv1 – open-source rewrite of Civ1
New top story on Hacker News: Undroidwish – a single-file, batteries-included Tcl/Tk binary for many platforms
Undroidwish – a single-file, batteries-included Tcl/Tk binary for many platforms
13 by smartmic | 1 comments on Hacker News.
13 by smartmic | 1 comments on Hacker News.
Friday, 27 March 2026
New top story on Hacker News: Byte Magazine Archive 1975 to 1995
Subscribe to:
Comments (Atom)