🧠 LLMs - CWhiting · Scour

Show HN: LLM post-training to speak like GenZ, costing less than a cup of coffee 🤖LLM

github.com·1d·Hacker News

China LLM Aggregation API 🤖LLM

chinawhapi.com·14h·DEV

AutoTTS: Researchers Cut Inference Tokens by 70% by Letting AI Write Its Own Strategy 🧠AI Models

firethering.com·4h·Hacker News

Using LLM in the shebang line of a script 🤖LLM

til.simonwillison.net·22h·Hacker News

Why LLMs Make Learning to Code More Important, Not Less 🤖LLM

senthil.learntosolveit.com·1d·Hacker News

Article: What are LLMs and Generative AI good at 🤖GenAI

jackpritz.com·3d·Hacker News

We Tested 10 Untested LLMs on Agent Coding 🤖LLM

dev.to·10h·DEV

Context Modification as a Negative Alignment Tax 🤖LLM

lesswrong.com·2d

JBS Dev: On imperfect data and the AI last mile – from model capability to cost sustainability 🏢Enterprise AI

artificialintelligence-news.com·1h

LATCH — Compiled Document Memory for LLMs 🤖LLM

codynamicslab.com·20h·Hacker News

Adola: Reducing LLM input tokens by 70% 🤖LLM

adola.app·3d·Hacker News, Hacker News

KV Caching in LLMs 🤖LLM

linkedin.com·2d·DEV

asakin/dragoman: A small CLI that lets Claude Code reach non-Anthropic models — Ollama, Perplexity, OpenAI, Gemini — through one verb the existing subagent runtime can call. 🤖Anthropic Claude

github.com·39m·Hacker News

Thinking Machines and interaction models 🛠️AI Tools

seangoedecke.com·16h·Hacker News

The Inference Shift 🤖LLM

stratechery.com·1d·Hacker News

The Determinism War: Why We Stopped Chasing Better Models 🛡️AI Safety

dev.to·2h·DEV

How do LLMs understand an artist's inner universe? 🤨AI Criticism

jimiwen.substack.com·12h·Substack

Are LLMs a Higher Level of Abstraction? No, And Here's Why 🤖LLM

hackernoon.com·3d

Better Search, Smaller Models: Why Retrieval Quality Beats Model Size 🤖Large Language Models

hackernoon.com·1d

Deep Learning Made Simple: What Neural Networks Actually Learn (Layer by Layer) 🤖Machine Learning

pub.towardsai.net

·4h

Log in to enable infinite scrolling