Building the Reasoning Engine at Axiom
axiommath.ai·12h·
Discuss: Hacker News
🎭Program Synthesis
I built a translator for spatial thinking (because I can't interview in Python)
graemefawcett.ca·13h·
Discuss: Hacker News
🎮Language Ergonomics
The key to conversational speech recognition
datasciencecentral.com·1d
🔍Tokenizers
Assuring Agent Safety Evaluations By Analysing Transcripts
lesswrong.com·22h
Effect Inference
Enhanced Predictive Maintenance of Geothermal Heat Exchangers via Hybrid Bayesian Optimization and LSTM
dev.to·3h·
Discuss: DEV
🔄Subinterpreters
Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks
machinelearning.apple.com·2d
📊LR Parsing
How the Rise of Tabular Foundation Models Is Reshaping Data Science
towardsdatascience.com·1d
🌱Minimal ML
LLMs and reinforcement learning
sicpers.info·22h
🪜Recursive Descent
From Text to Token: How Tokenization Pipelines Work
paradedb.com·1d
🔍Tokenizers
Zen of Python
webaligo.bearblog.dev·11h
🤐Zipper Structures
Towards privacy-aware mental health AI models
nature.com·16h
Effect Inference
Show HN: Using an LLM to sensibly sort a shopping receipt
treblig.org·1d·
Discuss: Hacker News
🪢Rope Algorithms
The Model That Broke All the Rules in Data Science
pub.towardsai.net·17h
🪜Recursive Descent
Show HN: Realization Jsmn on a Pure Zig
github.com·22h·
Discuss: Hacker News
📋JSON Parsing
From CAP to GAP?
fsharpforfunandprofit.com·1d·
Discuss: DEV
🧪Testing Compilers
LLMs Don’t Think. They Just Get Lucky.
pub.towardsai.net·2d
🌱Minimal ML
Functions are Asymmetric
elbeno.com·10h
😴Lazy Evaluation
Expanding the Action Space of LLMs to Reason Beyond Language
arxiv.org·1d
🪜Recursive Descent