🐿️ ScourBrowse
LoginSign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
📐 Proof Assistants

Agda, Coq, Isabelle, Lean, Theorem Proving, Interactive Verification

Eric MacAdie’s Elevator Pitch
irreal.org·4h
📺Terminal UI
Deep dive into Mojo object initialization
connorgray.com·3h·
Discuss: Hacker News
🦀Rust Borrowing
Wubular: Rubular Reimagined in Ruby+WASM
rubyelders.com·1d·
Discuss: Hacker News
🌀Brotli Internals
Making MCP Tool Use Feel Natural with Context-Aware Tools
ragie.ai·1d·
Discuss: Hacker News
🔗Constraint Handling
Using Real Survey Data to Create Authentic AI Personas for Extended Research
askrally.com·1d·
Discuss: Hacker News
🏛Digital humanities
Universal Algorithmic Intelligence
uaiasi.com·20h·
Discuss: Hacker News
🔲Cellular Automata
How to Build a ChatGPT Clone in Go: Cost, Context, and Lessons
nleiva.medium.com·2d·
Discuss: Hacker News
⚡gRPC
Fine-Tuning and Deploying GPT Models Using Hugging Face Transformers
blog.jetbrains.com·2d
🤖Grammar Induction
A Dynamic Approach to Collaborative Document Writing
arxiv.org·1d
🔗Parser Combinators
How to Summarize Huge Documents with LLMs: Beyond Token Limits and Basic Prompts
dev.to·1d·
Discuss: DEV
📝Text Compression
Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
arxiv.org·16h
🧮Kolmogorov Complexity
A beginner's guide to the Flux-Kontext-Max model by Black-Forest-Labs on Replicate
dev.to·18h·
Discuss: DEV
🎙️Whisper
Creating Wikipedia Search Embeddings with a Gaia Node
dev.to·1d·
Discuss: DEV
🏛Wikidata
VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
arxiv.org·16h
🔍Vector Forensics
CPU Branch Prediction – Earliest Forms of Machine Learning
medium.com·4h·
Discuss: Hacker News
⚡CPU Microarchitecture
Reasoning Steps as Curriculum: Using Depth of Thought as a Difficulty Signal for Tuning LLMs
arxiv.org·16h
🧮SMT Solvers
Autonomous AI testing agents are a bad idea
endform.dev·9h·
Discuss: Hacker News
🔍Concolic Testing
Show HN: Prompttest – Pytest for LLMs
github.com·2d·
Discuss: Hacker News
⚡Proof Automation
Benchmarking GPT-5 vs Claude 4 Sonnet on 200 Requests
dev.to·1d·
Discuss: DEV
⚙️Compression Benchmarking
Does GPT-4 surpass human performance in linguistic pragmatics?
arxiv.org·1d
🎙️Whisper
Loading...Loading more...
AboutBlogChangelogRoadmap