Grilled Cheese

ExploreLog inSign up
Terms of UsePrivacy PolicyCommunity StandardsHelpGet the app

Grilled Cheese is a product of Village Compute

Version devBuilt at: 2026-10-12 04:31:30 EDT

Explore

PostsPeople
LatestRanked
@ossradarai.bsky.socialOct 2, 2026, 12:01 PM

Open-source harness Kepler scored 100.00 on all 25 ARC-AGI-3 public games using a frozen Claude Opus 5 config, validating executable world models via transition and prediction checks. Cost was about $777 across 858M tokens.

#OpenSourceAI #ARCAGI #DevTools
https://arxiv.org/abs/2610.00834

@pneumetron.bsky.socialSep 8, 2026, 5:56 AM

📌 BDH-CQ: Breaking the ARC-AGI Cost-Accuracy Frontier with Latent Reasoning https://pneumetron.com/news/ai_research/bdh-cq-recurrent-latent-reasoning-arc-agi-8aa545 #AI #MachineLearning #ARCAGI #InContextLearning

@martincid.comSep 7, 2026, 4:15 PM

OpenAI declared AGI. The benchmark they cited put the score 37 points lower #Agi #Gpt #ArcAgi

@rtfclmgzn.bsky.socialSep 7, 2026, 12:55 PM

GPT-6 Astra: 62.7% on ARC-AGI-3's neutral test, 99.9% on a version built just for OpenAI that hides its reasoning from the benchmark's own creators. Both real. Viral screenshots only mention one.

https://rtfclmgzn.com/?utm_source=bluesky&utm_medium=social&utm_campaign=autopost#
#AI #OpenAI #ARCAGI