AI Briefing#arc-agi
The latest AI and developer news about #arc-agi, with the original source and a short summary.
The latest AI and developer news about #arc-agi, with the original source and a short summary.
GoBench, a benchmark evaluating LLM Go skills, has been released and is gaining attention as a reasoning metric due to its high correlation with ARC-AGI 2.
A small Transformer trained from scratch in 1.5 hours on a 5090 GPU achieved 44% on ARC-AGI, criticizing the low sample efficiency of LLMs.
A small transformer trained for 1.5 hours achieved 44% performance on the ARC-AGI-1 benchmark at a cost of 67 cents.
Introducing BDH-CQ, a system that demonstrates high efficiency on the ARC-AGI-1 benchmark through recurrent latent reasoning.
A 150M parameter recurrent latent reasoning model achieved high efficiency on ARC-AGI-1.
DeepSeek V4 Flash 0731 achieved 89.0% on ARC-AGI-1.
The ARC-AGI-3 leaderboard, which measures the adaptive intelligence of AI agents, has been released.
Anthropic unveiled an LLM reasoning tool called Schema, which achieved 99% performance on the ARC-AGI benchmark.
Adaption unveiled AutoScientist, showcasing automated model training.
Repeatedly updating memory as text failed to accumulate performance and instead collapsed it.
Seed IQ scored 100% on the ARC-AGI 3 benchmark through active inference instead of LLM scaling.