Hacker News - Newest: "LLM" hnrss.org

QUESTION/DISCUSSION: If this is the what is recommended by Karpathy, why is it not already part of the Claude Code thinking? · Issue #65 · forrestchang/andrej-karpathy-skills

github.com·3w·Hacker News

Agentic AI pentesting with Strix: results from 18 LLM models

theartificialq.github.io·3w·Hacker News

Talking to a local LLM in the Firefox sidebar

code.mendhak.com·3w·Hacker News

srk0102/plexa: One brain. Many bodies. Orchestration framework for embodied AI built on SCP. LangGraph for physical systems. Zero HTTP between bodies.

github.com·3w·Hacker News

Your intuition of LLM token usage might be wrong

blog.andreani.in·3w·Hacker News

Late-Bound Sagas: Why Your Agent Is Not an LLM in a Loop

medium.com·3w·Hacker News

Show HN: Bloomberg Terminal for LLM ops

news.ycombinator.com·3w·Hacker News

Show HN: Mcptube – Turn YouTube videos into AI-queryable MCP servers

github.com·9w·Hacker News, Hacker News

Show HN: Open KB: Open LLM Knowledge Base

news.ycombinator.com·3w·Hacker News

Your LLM is a compiler, not a runtime

getpocketbot.com·3w·Hacker News

Token optimized query language (Memelang)

memelang.net·7w·Hacker News, Hacker News

Unslop – Filter social media slop using local-first LLM classification

github.com·3w·Hacker News

Show HN: Formal – Formal verification for AI-generated code using Lean 4

github.com·3w·Hacker News, Hacker News

Beyond Karpathy's LLM-Wiki: The Necessity of Cognitive Governance

jonadas.com·3w·Hacker News

amitshekhariitbhu/llm-internals: Learn LLM internals step by step - from tokenization to attention to inference optimization.

github.com·3w·Hacker News

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers

arxiv.org·4w·Hacker News, Hacker News

parallem-ai/parallem: An expressive library for running agents with the Batch API.

github.com·3w·Hacker News

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

arxiv.org·3w·Hacker News, Hacker News

Show HN: Local LLM on a Pi 4 controlling hardware via tool calling

github.com·3w·Hacker News

Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception

arxiv.org·4w·Hacker News

Log in to enable infinite scrolling