Hacker News Reader

is there a paper or an article? the website is horrible and impossible to navigate.

cwegeneron Coffee for people who don't like coffee

The Clever Dripper is indeed a really neat invention. One of the old school specialty coffee guys in my city did recommend it. I have yet to move away from my french press though. I don't mind the little bit of extra effort of the french press.

since you're in the EU (I assume), check friedhats.com for some fancy roasts

EDIT: oh, and if you dont mind - what was the cheap grinder you got?

cwegeneron Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

I think the Coplit plugin is probably the closest thing to an AI IDE that actually works. As per my other comment, I don't actually use any IDE to begin with, but one of my coworkers who uses VSCode has been very fond of the latest iteration of the Copilot plugin.

From your description of how this plugin works, I see why it works so well. It is basically just focusing on the essentials (populating the appropriate context) and then does as best as it can to get out of the way ( <- this part is really important I think)

cwegeneron Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

I don't use IDEs to begin with. I use a text editor, since I am a UNIX man. So, I don't even have a reason to look at the "AI" flavor of an IDE. The closest thing to an AI IDE that I have tried out were tools like AIDER and Jack's "goose" agent. Neither of those specialized tools has been satisfactory. They all performed worse than just the LLM IMO. I am sticking to crafting my own context that I supply to the LLM. Tools like Simon W's `llm` tool help A LOT to be more efficient at using LLMs in a daily setting.

cwegeneron Llm.c – LLM training in simple, pure C/CUDA

Yes. CUDA is still entrenched due to its ease of use when compared to specialised AI hardware SDKs.

OpenMP is still a thing in 2024, but I presume that is not the kind of scale you are asking about.

If you have MI accelerators, you'll be using ROCm anyway (although AMD contracted Andrzej Janik in 2022 to make ZLUDA run on AMD GPUs. I have no idea what the practical applications of it are at the moment.)

The only other serious challenger (apart from the existing GPU manufactures like AMD) who is trying to give Nvidia a run for its money is Tenstorrent and their TT-Buda software kit.