Posts by nick@amok.recoil.org
(DIR) Post #ASi2536XxA1WfIi33Q by nick@amok.recoil.org
2023-02-15T16:29:36Z
0 likes, 2 repeats
@simon I find it so funny how within our lifetimes we've gone from the Turing test being some kind of impossible target to it being an incredible naive low bar because we're so easily fooled by a mirror
(DIR) Post #AT0hdVrn7IPkgGdf7Y by nick@amok.recoil.org
2023-02-24T16:39:56Z
0 likes, 0 repeats
@simon A friend of mine told me how jobs within prompt engineering would become a real thing, and I scoffed. Now I'm rapidly rethinking things
(DIR) Post #ATRkNA8mLjJY1Ree4O by nick@amok.recoil.org
2023-03-09T17:44:30Z
0 likes, 0 repeats
@simon I have a friend who's new to coding but wants to try out Python in a casual, beginner way. Are there any nice web-based tutorials? Perhaps with an editor in the actual page, so you see results as you go?
(DIR) Post #ATRoDbPEWRHBVO31c0 by nick@amok.recoil.org
2023-03-09T18:31:26Z
0 likes, 0 repeats
@simon cheers, that’s actually a good point. Pick an entry angle that’s aligned with your inherent interest in why programming is fun, and how you want to see it change the world in some way.
(DIR) Post #ATRsD4IK1tI2d1oeTw by nick@amok.recoil.org
2023-03-09T19:16:20Z
0 likes, 0 repeats
@simon I just came across a lovely notebook which introduces the basics of Python. I reckon loading that up in the try-jupyter link you posted would be a decent high level overview.https://gist.github.com/kenjyco/69eeb503125035f21a9d
(DIR) Post #AU7dV3mz4mbkpj5YsS by nick@amok.recoil.org
2023-03-29T22:49:38Z
0 likes, 0 repeats
@simon Huh. I wonder to what degree LoRA is introducing new possible output vs preventing lower quality responses. I guess it's more the latter?
(DIR) Post #AVJqtBvlfmENPBv7Ds by nick@amok.recoil.org
2023-05-04T17:52:42Z
0 likes, 0 repeats
@simon Have you played around with DeepFloyd yet? I've managed to get a 256x256 image out, but the final upscaler fails OOM
(DIR) Post #AVvIw6kXjxE0aJ6HoW by nick@amok.recoil.org
2023-05-22T19:46:57Z
0 likes, 0 repeats
@simon do you know the rough token generation speed? I’ve managed to get about 8-9/s from the recent updates to llama.cpp with BLAS offloading on my PC.
(DIR) Post #AVvJrS6n08L3KlqkXw by nick@amok.recoil.org
2023-05-22T19:57:21Z
0 likes, 0 repeats
@simon wow that’s considerably speedier!
(DIR) Post #AVvNiQZRkUfZm7CqBs by nick@amok.recoil.org
2023-05-22T20:40:29Z
0 likes, 0 repeats
@simon I got it working on my PC, and it's definitely faster than llama.cpp! I got prefill: 8.0 tok/s, decode: 38.7 tok/s. Very nice project, thanks for talking about it
(DIR) Post #AXcbBQuX5LqaQMddxo by nick@amok.recoil.org
2023-07-12T14:55:53Z
0 likes, 0 repeats
@simon Are you mostly doing your LLM work on the M2?
(DIR) Post #AZA3DNSs54etUfbGUK by nick@amok.recoil.org
2023-08-27T16:07:24Z
0 likes, 0 repeats
@simon perfect timing. I just got hold of a 128GB M1 and have got the basic large llama models working, but need to formalise it a bit more now
(DIR) Post #AaKoxrg81h9gLGa3Rg by nick@amok.recoil.org
2023-10-01T18:41:42Z
0 likes, 0 repeats
@simon To be fair I reckon that’s a hard image to classify full stop. I had to zoom in and stare for a few seconds before getting it
(DIR) Post #B0gTwlWihyvIzt59HM by nick@amok.recoil.org
2025-11-15T18:29:46Z
0 likes, 0 repeats
@benjojo Yeah, not for the likes of you, human