Manage episode 514893926 series 3641526
Feel free to leave feedback on Github: https://github.com/denolfe/hacker-news-highlights
- (00:00) - Intro
- (00:20) - Today is when the Amazon brain drain sent AWS down the spout
- (01:30) - Claude Code on the web
- (02:36) - A laser pointer at 2B FPS [video]
- (03:34) - Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system
- (04:50) - Production RAG: what I learned from processing 5M+ documents
- (06:03) - BERT is just a single text diffusion step
- (07:15) - ChkTag: x86 Memory Safety
- (08:33) - How to stop Linux threads cleanly
- (09:33) - My trick for getting consistent classification from LLMs
- (10:40) - x86-64 Playground – An online assembly editor and GDB-like debugger
- (11:51) - Outro
Today is when the Amazon brain drain sent AWS down the spout
https://www.theregister.com/2025/10/20/aws_outage_amazon_brain_drain_corey_quinn/
https://news.ycombinator.com/item?id=45649178
Claude Code on the web
https://www.anthropic.com/news/claude-code-on-the-web
https://news.ycombinator.com/item?id=45647166
A laser pointer at 2B FPS [video]
https://www.youtube.com/watch?v=o4TdHrMi6do
https://news.ycombinator.com/item?id=45632429
Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system
https://www.tomshardware.com/tech-industry/semiconductors/alibaba-says-new-pooling-system-cut-nvidia-gpu-use-by-82-percent
https://news.ycombinator.com/item?id=45643163
Production RAG: what I learned from processing 5M+ documents
https://blog.abdellatif.io/production-rag-processing-5m-documents
https://news.ycombinator.com/item?id=45645349
BERT is just a single text diffusion step
https://nathan.rs/posts/roberta-diffusion/
https://news.ycombinator.com/item?id=45644328
ChkTag: x86 Memory Safety
https://community.intel.com/t5/Blogs/Tech-Innovation/open-intel/ChkTag-x86-Memory-Safety/post/1721490
https://news.ycombinator.com/item?id=45582958
How to stop Linux threads cleanly
https://mazzo.li/posts/stopping-linux-threads.html
https://news.ycombinator.com/item?id=45589156
My trick for getting consistent classification from LLMs
https://verdik.substack.com/p/how-to-get-consistent-classification
https://news.ycombinator.com/item?id=45571423
x86-64 Playground – An online assembly editor and GDB-like debugger
https://x64.halb.it/
https://news.ycombinator.com/item?id=45646958
269 episodes