New pages
Jump to navigation
Jump to search
- 19:14, 7 August 2024 2024/web search (hist | edit) [1,070 bytes] DavidM (talk | contribs) (Created page with "I'm glad to see the US government ruling Google is a monopoly, but this could backfire. The one advantage of having a dominant player is everyone can exchange knowledge about it. That society level knowledge of 'web search' will be lost. It will hopefully be worth it for the sake of increased competition, choice and features, but it could just as well lead to arbitrary product mazes and walled gardens only some people can use, leading to more separation in society. On...")
- 18:23, 27 June 2024 2024/social media (hist | edit) [714 bytes] DavidM (talk | contribs) (Created page with "class=res-image|alt=Colosseum social media Centralization of social media is a modern problem, but it's not the only problem with current online discourse. Conversations are too much like a Colosseum event. You just want to make a minor point, next thing you know someone has their flame thrower trained at you, a few people in clown cars and trikes roll up and toss a couple random comments in. There are better systems. It's a mystery w...")
- 14:23, 13 April 2024 2024 llama.cpp 7840u (hist | edit) [5,364 bytes] DavidM (talk | contribs) (Created page with "I briefly had a Macbook M3 Max with 64GB. It was pretty good at running local LLMs, but couldn't stand the ergonomics and not being able to run Linux, so returned it. I picked up a Thinkpad P16s with an AMD 7840 to give Linux hardware a chance to catch up with Apple silicon. It's an amazing computer for the price, and can run LLMs. Here's how I set up llama.cpp to use ROCm. Install ROCm, set an env variable for the 780m: <code>export HSA_OVERRIDE_GFX_VERSION=11.0.0</co...")
