GPT-6 Astra(openai.com)
2200 points by kibae | 2013 comments
OpenAI's announcement page for its GPT-6 Astra model, showing a hero graphic with the model name over a spiral galaxy image.
#arc-agi on Hacker News
8 stories tagged arc-agi, newest first.
I trained a small transformer in 1.5hrs and it beats many LLMs(mvakde.github.io)
578 points by porridgeraisin | 149 comments
Personal blog post describing a small transformer trained from scratch in 1.5 hours on an RTX 5090 that scores 44% on ARC-AGI-1 for 67 cents.
DeepSeek V4 Flash 0731(arcprize.org)
761 points by tosh | 454 comments
ARC Prize verified results page for DeepSeek V4 Flash 0731, reporting its ARC-AGI-1 and ARC-AGI-2 scores and cost per task on a leaderboard chart.
ARC-AGI without pretraining(iliao2345.github.io)
331 points by georgehill | 90 comments
Blog post by Isaac Liao and Albert Gu describing a method that solves ARC-AGI puzzles using lossless information compression without pretraining.
An analysis of DeepSeek's R1-Zero and R1(arcprize.org)
703 points by meetpateltech | 257 comments
ARC Prize blog post by Mike Knoop analyzing DeepSeek's R1-Zero and R1 models, arguing R1-Zero is more important, with ARC-AGI benchmark results.
OpenAI O3 breakthrough high score on ARC-AGI-PUB(arcprize.org)
1578 points by maurycy | 1581 comments
ARC Prize blog post by François Chollet reporting OpenAI's o3 scoring 75.7% (and 87.5% at high compute) on the ARC-AGI semi-private evaluation set.
Getting 50% (SoTA) on Arc-AGI with GPT-4o(redwoodresearch.substack.com)
359 points by tomduncalf | 195 comments
Redwood Research blog post by Ryan Greenblatt describing reaching 50% on the ARC-AGI public test set by sampling thousands of GPT-4o-generated Python programs.
ARC Prize – a $1M+ competition towards open AGI progress(arcprize.org)
527 points by mikeknoop | 266 comments
Blog post announcing ARC Prize, a $1M+ public competition by Mike Knoop and François Chollet to beat and open-source a solution to the ARC-AGI benchmark.