GoKawiil
Paper Tape Is All You Need – Training a Transformer on a 1976 Minicomputer
(news.ycombinator.com)
121.
123.
LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language?
(news.ycombinator.com)
124.
125.
Intuitions for Tranformer Circuits
(news.ycombinator.com)
126.
127.
128.
129.
Show HN: I ran a language model on a PS2
(news.ycombinator.com)
133.
Fire Phone 2.0? Amazon wants a second chance at failing to make a phone work
(androidauthority.com)
134.
Attention Residuals
(news.ycombinator.com)
135.
138.
139.
Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
(news.ycombinator.com)
140.
141.
Why Resilient, Mentally Healthy Employees Drive Unstoppable Performance
(feeds.feedburner.com)
142.
Nvidia says it can shrink LLM memory 20x without changing model weights
(venturebeat.com)
143.
144.
Executing programs inside transformers with exponentially faster inference
(news.ycombinator.com)
145.
146.
Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
(news.ycombinator.com)
147.
Show HN: How I Topped the HuggingFace Open LLM Leaderboard on Two Gaming GPUs
(news.ycombinator.com)
148.
149.
Finite-Element Approaches to Transformer Harmonic and Transient Analysis
(spectrum.ieee.org)
150.
10-202: Introduction to Modern AI (CMU)
(news.ycombinator.com)