Local LLM App by Ente
(news.ycombinator.com)
121.
122.
Local LLM by Ente
(news.ycombinator.com)
123.
Towards end-to-end automation of AI research
(feeds.nature.com)
124.
How xMemory cuts token costs and context bloat in AI agents
(venturebeat.com)
125.
Welcome to FastMCP
(news.ycombinator.com)
126.
Popular LiteLLM PyPI package backdoored to steal credentials, auth tokens
(bleepingcomputer.com)
127.
Popular LiteLLM PyPI package compromised in TeamPCP supply chain attack
(bleepingcomputer.com)
128.
Hypura – A storage-tier-aware LLM inference scheduler for Apple Silicon
(news.ycombinator.com)
129.
LiteLLM Python package compromised by supply-chain attack
(news.ycombinator.com)
130.
Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised
(news.ycombinator.com)
131.
LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language?
(news.ycombinator.com)
132.
133.
134.
Autoresearch on an old research idea
(news.ycombinator.com)
135.
I tried Karpathy's Autoresearch on an old research project
(news.ycombinator.com)
136.
iPhone 17 Pro Demonstrated Running a 400B LLM
(news.ycombinator.com)
137.
138.
Brute-Forcing My Algorithmic Ignorance with an LLM in 7 Days
(news.ycombinator.com)
139.
We rewrote our Rust WASM parser in TypeScript and it got faster
(news.ycombinator.com)
140.
AI Conundrum: Why MCP Security Can't Be Patched Away
(darkreading.com)
141.
No AI in Node.js Core
(news.ycombinator.com)
142.
143.
I turned Markdown into a protocol for generative UI
(news.ycombinator.com)
144.
2% of ICML papers desk rejected because the authors used LLM in their reviews
(news.ycombinator.com)
145.
Ask HN: How do you deal with people who trust LLMs?
(news.ycombinator.com)
146.
148.
Give Django your time and money, not your tokens
(news.ycombinator.com)
149.
150.
How I write software with LLMs
(news.ycombinator.com)