Father son duo medalling on the ARC Prize with Hark!
Summary
A father-son duo used the newly released hark.com to semi-autonomously iterate on notebooks for days, achieving a medalling result on the ARC Prize and highlighting how AI can lower the barrier to entry.
Similar Articles
@dair_ai: NEW paper worth reading. (bookmark it) Autonomous research systems usually prove themselves on cherry-picked wins, huma…
FARS is a fully automated research system that uses stage-specific AI agents to handle ideation, planning, experimentation, and writing, producing 166 complete research papers across 67 AI/ML topics in its first public deployment.
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
AutoResearchClaw is a multi-agent autonomous research system that improves scientific discovery through structured debate, self-healing execution, and human collaboration, outperforming previous systems on the ARC-Bench benchmark by 54.7%.
@AIatMeta: As a test of our progress to advance the frontier of AI research, in June we entered the next generation of our autonom…
Meta's autonomous AI research system AIRA₃ placed 8th out of approximately 4,000 teams to win gold in a NVIDIA Kaggle competition to fine-tune a 30B Nemotron model, outperforming human competitors with access to the same tools.
@RoundtableSpace: HUGGING FACE JUST AUTOMATED THEIR ENTIRE POST-TRAINING TEAM WITH AN AGENT. It reads papers, runs GPU experiments, itera…
Hugging Face replaced its post-training team with an autonomous agent that reads papers, runs GPU experiments, and improves models, achieving a 22-point benchmark jump in under 10 hours and beating Codex on HealthBench by 60%.
@dair_ai: https://x.com/dair_ai/status/2068724104815890889
Highlights three recent AI papers: SpatialClaw (training-free spatial reasoning via code), SkillWeaver (compositional skill routing with decompose-retrieve-compose pipeline), and PreAct (compiling agent runs into fast state machines for repeated tasks).