Reworking Memory Management in CRuby
railsatscale.com·5h·
Discuss: Hacker News
🧠Memory Allocators
Claude Can (Sometimes) Prove It
galois.com·8h·
🧩Constraint Solvers
Chapter 1: LLM Fundamentals
cline.ghost.io·16h
🎮Language Ergonomics
Pursuing a Trick a Long Way Just to See Where It Goes, with Simon Peyton Jones
popovit.ch·2d·
Discuss: Hacker News
functional programming
De-risking investment in AI agents - MIT Technology Review
news.google.com·18h
🌲Deforestation
[ARC-AGI-2 SoTA] Efficient Evolutionary Program Synthesis
ctpang.substack.com·2h·
Discuss: Substack
🔍ML Language
Stumbling into AI: Part 4—Terminology Tidy-up (and a little rant)
rmoff.net·15h
🌱Minimal ML
AutoOEP -- A Multi-modal Framework for Online Exam Proctoring
arxiv.org·1d
🎯Finite Automata
Learn How to Use Transformers with HuggingFace and SpaCy
towardsdatascience.com·1d
📊Pratt Parsers
Gradient Free Deep Reinforcement Learning With TabPFN
arxiv.org·1d
🪜Recursive Descent
Increasing alignment of large language models with language processing in the human brain
nature.com·21h
🪜Recursive Descent
On the Regularity and Fairness of Combinatorial Multi-Armed Bandit
arxiv.org·3h
🗺️Region Inference
When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning
arxiv.org·3h
🪜Recursive Descent
Spec-Driven Development in a Startup
pub.towardsai.net·15h
🎮Language Ergonomics
Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
arxiv.org·3h
🪜Recursive Descent
Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models
arxiv.org·3h
🎯Finite Automata
Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction
arxiv.org·3h
🔗Unification
What is Algebraic about Algebraic Effects?
interjectedfuture.com·1d
💫Effect Systems