LLMs and reinforcement learning
sicpers.info·1d
⚔️Lean Tactics
Toy Binary Decision Diagrams
philipzucker.com·5d
🧮Algebraic Datatypes
Beyond the Hyped IMO Benchmarks: Towards a True Mathematical AI Discovery
quantumformalism.substack.com·1d·
Discuss: Substack
🧮SMT Solvers
When Python can't thread: a deep-dive into the GIL's impact
pythonspeed.com·1d·
Discuss: Hacker News
🔩Systems Programming
AI as both authors and reviewers of research papers
openreview.net·1d·
Discuss: Hacker News
🔲Cellular Automata
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
arxiv.org·1d
🧮Kolmogorov Complexity
Valid Stopping for LLM Generation via Empirical Dynamic Formal Lift
arxiv.org·2d
💻Programming languages
AI Just Killed Traditional Coding - Here's What's Next
dev.to·8h·
Discuss: DEV
🌳Incremental Parsing
Haskell Weekly Issue 493
haskellweekly.news·2d·
Discuss: Hacker News
🧬Functional Programming
Intent Weaving for AI Coding Agents
autohand.ai·1d·
Discuss: Hacker News
⚡Proof Automation
On the Pure Quantum Polynomial Hierarchy and Quantified Hamiltonian Complexity
arxiv.org·2d
⚛️Quantum Algorithms
Intro to RL: Off-Policy Methods
neelsomaniblog.com·2d·
Discuss: Hacker News
🔲Cellular Automata
Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph
arxiv.org·4d
⚡Proof Automation
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·2d
🔨Compilers
Every Line of Code Is a Philosophy in Disguise
dev.to·1d·
Discuss: DEV
⚖️Emulation Ethics
Show HN: Realization Jsmn on a Pure Zig
github.com·1d·
Discuss: Hacker News
🔗Concatenative Programming
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·1h·
Discuss: DEV
📊Multi-vector RAG
The Library Method: Understanding @cache
dev.to·1d·
Discuss: DEV
⚡Cache Theory
I Built the Perfect Workflow and attracted some friends in the process
graemefawcett.ca·14h·
Discuss: Hacker News
⚡Proof Automation
Categorical Invariants of Learning Dynamics
arxiv.org·4d
🕸️Algebraic Topology