Large Language Models, GPT, Transformers, Prompting

Live Conversational Threads: Not an AI Notetaker
lesswrong.com·5h
💬Prompt Engineering
Flag this post
Adaptive Stemming via Graph-Augmented Recurrent Variational Autoencoders
dev.to·1d·
Discuss: DEV
💬Natural Language Processing
Flag this post
Polish emerges as top language in multilingual AI benchmark testing
ppc.land·1d
📝NLP
Flag this post
Beyond the Magic: How LLMs Work
tag1.com·5d·
Discuss: Hacker News
💬Prompt Engineering
Flag this post
Kimi Linear: An Expressive, Efficient Attention Architecture
arxiviq.substack.com·1d·
Discuss: Substack
💬Prompt Engineering
Flag this post
Generation at the Speed of Thought: Speculative Decoding
bittere.substack.com·23h·
Discuss: Substack
💬Prompt Engineering
Flag this post
Small Vs. Large Language Models
semiengineering.com·2h
💬Prompt Engineering
Flag this post
Practical Steps Towards Vibe Writing with AI Positron
blog.oxygenxml.com·22h
💬Prompt Engineering
Flag this post
Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
arxiv.org·5h
📝NLP
Flag this post
Parsing with zippers improves parsing with derivatives
dl.acm.org·1d·
Discuss: Hacker News
💬Natural Language Processing
Flag this post
Synthesized Generative Modeling via Graph-Constrained Semantic Embedding
dev.to·17h·
Discuss: DEV
💬Prompt Engineering
Flag this post
LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints
arxiv.org·5h
📝NLP
Flag this post
From hours to seconds: AI tools to detect animal calls
seangoedecke.com·1d·
Discuss: Hacker News
🧠Machine Learning
Flag this post
Beyond the Black Box: Making LLM Decoding Truly End-to-End
dev.to·2d·
Discuss: DEV
💬Prompt Engineering
Flag this post
Deploy an LLM inference service on OpenShift AI
developers.redhat.com·3h
💬Prompt Engineering
Flag this post
Semantic search with embeddings in PHP: a hands-on guide using Neuron AI and Ollama
ollama.com·1d·
Discuss: DEV
💬Natural Language Processing
Flag this post
Meta's Free Transformer introduces a new approach to LLM decision-making
the-decoder.com·1d
💬Prompt Engineering
Flag this post
ParallelBench: Understanding the Trade-offs of Parallel Decoding in DiffusionLLMs
dev.to·15h·
Discuss: DEV
💬Prompt Engineering
Flag this post
I made a tensor runtime & inference framework in C (good for learning how inference works)
github.com·9h·
🤖AI
Flag this post
Speedrunning an RL Environment
sidb.in·1d·
Discuss: Hacker News
💬Prompt Engineering
Flag this post