Sorting Prompts - LLMs are not wrong you just caught them mid thought
kau.sh·14h
⚡Proof Automation
Is ChatGPT-5 Able to Provide Proofs for Advanced Mathematics?
machinelearningmastery.com·3d
🎯Proof Tactics
YouTube gets ~5% CTR lift on Shorts by replacing embedding tables with Semantic IDs
shaped.ai·1d
📊Feed Optimization
The Porcelain to Come
stackdiver.com·8h·
Discuss: Hacker News
🔲Cellular Automata
Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media
arxiv.org·1d
💾Binary Linguistics
IKNet: Interpretable Stock Price Prediction via Keyword-Guided Integration of News and Technical Indicators
arxiv.org·1d
🧠Learned Indexing
94% of Developers Waste Tokens on Reasoning LLMs. Here's Why.
dev.to·1d·
Discuss: DEV
💻Local LLMs
Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
arxiv.org·1d
🧠Machine Learning
Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
arxiv.org·1d
🎯Content Recommendation
Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
arxiv.org·4d
🔗Parser Combinators
Effective and Stealthy One-Shot Jailbreaks on Deployed Mobile Vision-Language Agents
arxiv.org·1d
🕵️Vector Smuggling
Revisiting Long-context Modeling from Context Denoising Perspective
arxiv.org·3d
🔢Denotational Semantics
How Google Translate & ChatGPT Work: The Transformer, Unboxed
dev.to·1d·
Discuss: DEV
🧠Learned Codecs
A Manifesto for the Programming Desperado
github.com·15h·
Discuss: Hacker News
💻Programming languages
Causality Guided Representation Learning for Cross-Style Hate Speech Detection
arxiv.org·1d
🎙️Whisper
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
arxiv.org·1d
💻Local LLMs
Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers
arxiv.org·1d
✓Automated Theorem Proving
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
arxiv.org·3d
🧮Kolmogorov Complexity
Graph-based LLM over Semi-Structured Population Data for Dynamic Policy Response
arxiv.org·3d
💻Local LLMs
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.org·1d
⚡Proof Automation