Frozen in Place
economics.bmo.com·1d·
Discuss: Hacker News
🔄Subinterpreters
Flag this post
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
machinelearning.apple.com·1d
🪜Recursive Descent
Flag this post
We need to give LLMs human-like vision
matml.bearblog.dev·2h·
🌱Minimal Interpreters
Flag this post
Entropy in algorithm analysis
11011110.github.io·2d
🧮Combinator Calculus
Flag this post
original ↗
raymondcamden.com·1d
📝Rope Editors
Flag this post
Defeating KASLR by Doing Nothing at All
googleprojectzero.blogspot.com·1d·
📏Linear Memory
Flag this post
I Use AI
ben.stolovitz.com·4h·
Discuss: Hacker News
💬Interactive REPLs
Flag this post
Mitigating Semantic Collapse in Partially Relevant Video Retrieval
arxiv.org·1d
🗂️Term Indexing
Flag this post
Probabilistic Robustness for Free? Revisiting Training via a Benchmark
arxiv.org·13h
⚖️Weighted Automata
Flag this post
Predicting & Mitigating Data Corruption in Pure Storage Flash Arrays via Adaptive Bit Error Rate Modeling
dev.to·8h·
Discuss: DEV
🧠Memory Ordering
Flag this post
Writing Your First Compiler - Part 1: Introduction
dev.to·1d·
Discuss: DEV
🏗️Minimal Compilers
Flag this post
The case against pgvector
simonwillison.net·22h
🔍Query Engines
Flag this post
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
arxiv.org·13h
🪜Recursive Descent
Flag this post
🧠 Smart Text Matching: RapidFuzz vs Difflib
dev.to·1d·
Discuss: DEV
🔍Fuzzy Matching
Flag this post
Unlocking LLMs: The Self-Steering Revolution
dev.to·2d·
Discuss: DEV
🪜Recursive Descent
Flag this post
Efficient Test-Time Retrieval Augmented Generation
arxiv.org·13h
🎲Parser Fuzzing
Flag this post
A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
arxiv.org·13h
🪜Recursive Descent
Flag this post
Show HN: I built a CLI tool to automatically break up large PRs
github.com·2h·
Discuss: Hacker News
🚂Cranelift Backend
Flag this post