Evaluating Gemini 2.5 Deep Think's math capabilities
epoch.ai·20h·
Discuss: Hacker News
🧩Constraint Solvers
Randomized and quantum approximate matrix multiplication
arxiv.org·1d
🔬Nanopasses
Nonlinear phase gates as Airy transforms of the Wigner function
nature.com·20h
∀Quantified Types
What Large Language Models Teach Us About 'Human Knowledge'
opengovernance.net·8h
🌱Minimal ML
LINQ and Learning to Be Declarative
nickstambaugh.dev·1d·
Discuss: Hacker News
📋Datalog
Title: The Complexity of ChatGPT's Model Picker: A Comprehensive Analysis
dev.to·1d·
Discuss: DEV
🔄Subinterpreters
RND1: Simple, Scalable AR-to-Diffusion Conversion
radicalnumerics.ai·1d·
Discuss: Hacker News
🔬Nanopasses
IASC: Interactive Agentic System for ConLangs
arxiv.org·1d
🔄Incremental Lexing
The Bit Shift Paradox: How "Optimizing" Can Make Code 6× Slower
hackernoon.com·3d
⚡Interpreter Optimization
Contrastive Weak-to-strong Generalization
arxiv.org·1d
🪜Recursive Descent
Ship Broken Things
matmul.net·1d·
Discuss: Hacker News
🌳Tree Shaking
An enough week
blog.mitrichev.ch·1d·
Discuss: blog.mitrichev.ch
🧩Constraint Solvers
How static analysis encourages developers to refactor code: Another look at Source SDK
dev.to·19h·
Discuss: DEV
🪄C Metaprogramming
New memory framework builds AI agents that can handle the real world's unpredictability
venturebeat.com·2d
🧠Memory Ordering
H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
arxiv.org·3d
🗺️Region Inference
On Limits on the Provable Consequences of Quantum Pseudorandomness
eprint.iacr.org·3d
🧮Combinator Calculus
The Conveyor Belt Protocol: Understanding Iterators
dev.to·6h·
Discuss: DEV
🪢Rope Data Structures
P-adic numbers and kernels
arxiv.org·1d
🧮Combinator Calculus
Exponential Error Bounds for Information Bottleneck Source Coding Problems
arxiv.org·1d
📦Compression Algorithms
AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
arxiv.org·1d
📋JSON Parsing