Hacker News - Newest: "LLM" hnrss.org

victornominista/anp: The economic layer for agent-to-agent negotiation. Binary protocol, Ed25519 identity, price oracle.

github.com·6d·Hacker News

lazyville/qsh: q - Slim LLM CLI

github.com·6d·Hacker News

We upgraded to a frontier model and our costs went down

mendral.com·8w·Hacker News, Hacker News

Ask HN: What happens when you paste a screenshot, and ask questions in LLM?

news.ycombinator.com·6d·Hacker News

Monitoring LLM behavior: Drift, retries, and refusal patterns

venturebeat.com·1w·Hacker News

gfernandf/agent-skills: Agents should execute whenever possible — runtime for composable AI agent skills

github.com·5w·Hacker News, Hacker News

Understanding the LLM Bubble

americanaffairsjournal.org·10w·Hacker News, Hacker News

LLM Budget Guard – open-source runtime cutoff for OpenAI/Anthropic

llmeter.org·6d·Hacker News

vnmoorthy/pavo-bench: A 50K-turn voice pipeline benchmark and an 85K-param meta-controller that cuts P95 latency 10.3% and energy 71% vs fixed cloud. TMLR 2026.

github.com·6d·Hacker News

redcaller/voice-goat: A purposely vulnerable voice agent application for security practitioners to practice exploiting voice-based (and text based) AI systems.

github.com·6d·Hacker News

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

arxiv.org·2w·Hacker News

LLM from pre-1930 derives quantum mechanics and relativity

michaelhla.com·6d·Hacker News

xoai/sage-wiki: An LLM-compiled personal knowledge base. Drop in your papers, articles, and notes. sage-wiki compiles them into a structured, interlinked wiki — with concepts extracted, cross-references discovered, and everything searchable.

github.com·6d·Hacker News

MTimma/knowerage: Local MCP server that tracks AI analysis coverage against your codebase

github.com·6d·Hacker News

A Primer on LLM Post-Training

pytorch.org·6d·Hacker News

Why the same LLM gives different answers in different environments

johndwade.substack.com·1w·Substack

epscylonb/1386.ai.rocm: A lightweight transformer language model built from scratch in PyTorch, trained on a single consumer GPU with a full pipeline for data processing, pretraining, and instruction tuning.

github.com·1w·Hacker News

MCP server that rewrites vague prompts before they reach the LLM

preprompt.org·1w·Hacker News

I build my LLM a Brain

news.ycombinator.com·1w·Hacker News

glama-ai/lightport: A lightweight AI gateway that makes LLM providers OpenAI-compatible.

github.com·1w·Hacker News

Log in to enable infinite scrolling