Hacker News - Newest: "LLM" hnrss.org

skorotkiewicz/firefox-ai: For any (and only) OpenAI compatible APIs

github.com·2w·Hacker News

Show HN: Idea File for LLM Cycling Coach

gist.github.com·2w·Hacker News

bolnet/agent-memory: Embedded memory for AI agents. SQLite + pgvector + Neo4j. Sub-5ms retrieval.

github.com·2w·Hacker News

Deep Dive into Efficient LLM Inference with Nano-vLLM

cefboud.com·4w·Hacker News

menot-you/llm-as-dom: LLM-as-DOM — AI browser pilot. Cheap LLM navigates the web so expensive models don't have to.

github.com·2w·Hacker News

One Layer, +12%: What 667 Configs Reveal About Small LLM Anatomy

austinsnerdythings.com·2w·Hacker News, Hacker News

Sandyaa: Recursive-LLM source code auditor that writes exploitable PoCs

github.com·2w·Hacker News

Cut Checkpoint Costs with About 30 Lines of Python and NVIDIA nvCOMP

developer.nvidia.com·3w·Hacker News

distributed-semantic-cache/docs/blog/three-layer-cache-architecture.md at main · kylemaa/distributed-semantic-cache

github.com·3w·Hacker News

Context Rot: How Increasing Input Tokens Impacts LLM Performance

trychroma.com·5w·DEV, Hacker News

hipvlady/agent-coherence: Arbiter — The Coherence Protocol for AI Agents

github.com·3w·Hacker News

LLM inference engine written ground-up natively in C#/.NET

dotllm.dev·3w·Hacker News

The Missing Context Layer: Why Your LLM Agent Can't Do More Than Text-to-SQL

airbyte.com·3w·Hacker News

Job Matcher – LLM-scored job listings from 10 boards, self-hosted

christopherbeaulieu.net·3w·Hacker News

Show HN: A tool to compare LLM costs for typical coding domains

the-designengineer.com·3w·Hacker News

Find and Fix AI Agent & LLM App Failures — Automatically | Kelet

kelet.ai·3w·Hacker News

Introducing dotLLM - Building an LLM Inference Engine in C#

kokosa.dev·3w·Hacker News, Hacker News

Same LLM, Different Agent: What Changes When You Specialize for CI

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

KillBench: Every frontier LLM is biased about who deserves to live

whitecircle.ai·3w·Hacker News

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

Log in to enable infinite scrolling