Show HN: Linguistic RL – A 7B model discovers Occam's Razor through reflection
github.com·25m·
Discuss: Hacker News
🤖AI
Flag this post
DS-STAR: A state-of-the-art versatile data science agent
research.google·21h·
Discuss: Hacker News
🤖AI
Flag this post
Mathematical exploration and discovery at scale
terrytao.wordpress.com·1d·
Discuss: Hacker News
🤖AI
Flag this post
The Curved Spacetime of Transformer Architectures
arxiv.org·1d·
Discuss: Hacker News
🤖AI
Flag this post
AI Agent Guides from Google, Anthropic, Microsoft, etc. Released This Week
sarthakai.substack.com·17h·
Discuss: Substack
🤖AI
Flag this post
Continuous Autoregressive Language Models
shaochenze.github.io·2d·
Discuss: Hacker News
🤖AI
Flag this post
Modern Optimizers – An Alchemist's Notes on Deep Learning
notes.kvfrans.com·9h·
Discuss: Hacker News
🤖AI
Flag this post
Harness the Power of Atlas Search and Vector Search with $RankFusion
mongodb.com·1d·
Discuss: Hacker News
🤖AI
Flag this post
Reasoning with Sampling: Your Base Model Is Smarter Than You Think
aakaran.github.io·22h·
Discuss: Hacker News
🤖AI
Flag this post
AI's capabilities may be exaggerated by flawed tests, according to new study
nbcnews.com·1d·
Discuss: Hacker News
🤖AI
Flag this post
Improving agent with semantic search Semantic search significantly improves coding agent performance with 12.5% higher accuracy, improves code retention and dec...
cursor.com·1d·
Discuss: Hacker News
🤖AI
Flag this post
GEN-0: SoTA 10B+ Foundation Model for Robotics with Harmonic Reasoning
generalistai.com·2d·
Discuss: Hacker News
🤖AI
Flag this post
Automating error analysis for AI agents – what works and doesn't
atla-ai.com·3d·
Discuss: Hacker News
🤖AI
Flag this post
Generalizing Test-Time Compute-Optimal Scaling as an Optimizable Graph
huggingface.co·2d·
Discuss: Hacker News
🤖AI
Flag this post
Run LLMs Locally
ikangai.com·1d·
Discuss: Hacker News
🤖AI
Flag this post
Generation of antigen-specific paired-chain antibodies using LLMs
sciencedirect.com·22h·
Discuss: Hacker News
🤖AI
Flag this post
Benchmarking the Most Reliable Document Parsing API
tensorlake.ai·21h·
Discuss: Hacker News
🤖AI
Flag this post
SampCert: Verified Foundations for Differential Privacy (PLDI 2025)
dl.acm.org·23h·
Discuss: Hacker News
🤖AI
Flag this post
The Complexity Cliff: Why Reasoning Models Work Right Up Until They Don't
rewire.it·1d·
Discuss: Hacker News
🤖AI
Flag this post
We Started with Jax but Moved to PyTorch
mlechner.substack.com·22h·
Discuss: Substack
🤖AI
Flag this post