| | Writing an LLM from scratch, part 9 – causal attention (gilesthomas.com) |
|
4 points by gpjt 4 days ago | past | discuss
|
| | Writing an LLM from scratch, part 8 – trainable self-attention (gilesthomas.com) |
|
379 points by gpjt 9 days ago | past | 31 comments
|
| | It’s still worth blogging in the age of AI (gilesthomas.com) |
|
333 points by gpjt 17 days ago | past | 223 comments
|
| | The benefits of learning in public (gilesthomas.com) |
|
311 points by gpjt 18 days ago | past | 97 comments
|
| | Getting MathML to render properly in Chrome-based browsers (gilesthomas.com) |
|
3 points by LorenDB 25 days ago | past
|
| | Do reasoning LLMs need their own Philosophical Language? (gilesthomas.com) |
|
1 point by gpjt 56 days ago | past | 1 comment
|
| | Messing around with fine-tuning LLMs, detailed memory usage for an 8B model (gilesthomas.com) |
|
1 point by vednig 6 months ago | past
|
| | LLM Quantisation Weirdness (gilesthomas.com) |
|
2 points by gpjt on Feb 28, 2024 | past
|
| | Pam-unshare: a PAM module that switches into a PID namespace (gilesthomas.com) |
|
5 points by gpjt on April 15, 2016 | past
|
| | Does #EUVAT make charging Bitcoin impossible for EU digital services businesses? (gilesthomas.com) |
|
3 points by gpjt on Dec 20, 2014 | past
|
| | How many python programmers are there in the World today? (gilesthomas.com) |
|
1 point by lifeisstillgood on May 8, 2014 | past | 2 comments
|
| | SNI-based Reverse Proxying for SSL connections (gilesthomas.com) |
|
1 point by chesh on July 23, 2013 | past | 1 comment
|
| | How to bet on the bubble? (with list of 2010/11 YC startup hosting providers) (gilesthomas.com) |
|
1 point by gpjt on March 30, 2011 | past | 7 comments
|
| | Fun with Google Books Ngram Viewer and the long S (gilesthomas.com) |
|
2 points by gpjt on Dec 17, 2010 | past
|
| | IT headhunters considered harmful (gilesthomas.com) |
|
7 points by j_baker on Jan 10, 2010 | past | 1 comment
|