notpublic

Jackrong has published the finetuning steps here. It seems to be quite thorough with notebooks etc. I am going through it myself now...

https://github.com/R6410418/Jackrong-llm-finetuning-guide

Excellent talk!

Thanks! I assume you are referring to this https://github.com/obra/superpowers

I use it as well (a customized version suited for my worflow). It is indeed the GOAT.

From the commit history, it looks like you are using Claude for some of the development. Would love to hear how you are using Claude to go through such a massive code base.

btw, impressive project.

Bestbuy with local pickup. They price match Amazon. B&H Photo is another option.

Thanks! In my search for a good STL for the following, your app gave me the closest model so far!

https://m.media-amazon.com/images/I/41hGjsBlrKL._AC_SL1000_....

I tried Google/Claude etc. But none worked. As per Claude, the technical name for that is Pillow Block Bearing/Shaft Coupling Block/Flange Mount Bracket. Funny thing is, your app didn't return any good result when I search with any of those terms.

After reading your blog post, I searched for "block with 2 holes". And lo and behold, it returned ABC-00162357!

Couple of suggestions: 1) Have a permanent link for each model 2) Show related models when a model is clicked 3) and lastly, show models based on an image

edit: Search for "mounting block" returned ABC-00180735 which is exactly what I was looking for. Thank you so much for making this!

Offline videos are available here: https://video.fosdem.org/2026

It's organized by room which you can find here: https://fosdem.org/2026/schedule/tracks/

Yep. You be right. Looks like they increased it earlier this month. Bummer!

Talking about RAM prices, you can still get a framework Max+ 395 with 128GB RAM for ~$2,459 USD. They have not increased the price for it yet.

https://frame.work/products/desktop-diy-amd-aimax300/configu...

Is it fair to say IPV6 with ULA (Unique Local Addresses) is best of both worlds?

Try adding a session hook that triggers on startup|resume|clear|compact to remind Claude about your custom skills.

Another thing that helps is adding a session hook that triggers on startup|resume|clear|compact to remind Claude about your custom skills. Keeps things consistent, especially when you're using it for a long time without clearing context

Instead of including all these instructions in CLAUDE.md, have you considered using custom Skills? I’ve implemented something similar, and Skills works really well. The only downside is that it may consume more tokens.

Check out the following for AM5 motherboards. It helped me a lot when I was in the market. Seems to be well maintained still:

https://docs.google.com/spreadsheets/d/1NQHkDEcgDPm34Mns3C93...

I ended up getting ASRock X870E Taichi Lite. The main reason to get it was because it had 2 CPU x8 slots which are spaced perfectly for an Nvidia NVLink. And, they are Gen5 PCIe.

What is the proper way to disclose evidence for this class of hacking?

If you know what to look for, the report actually has quite a few details on how they did it. In fact, when the report came out, all it did was confirm my suspicions.

"A report was recently published by an AI-research company called Anthropic. They are the ones who notably created Claude, an AI-assistant for coding. Personally, I don’t use it but that is besides the point."

Not sure if the author has tried any other AI-assistants for coding. People who haven't tried coding AI assistant underestimates its capabilities (though unfortunately, those who use them overestimate what they can do too). Having used Claude for some time, I find the report's assertions quite plausible.

Indeed! I just found out about tmux display-popup recently.

  # ~/.tmux.conf 
  bind-key C-g display-popup -E -d "#{pane_current_path}" -xC -yC -w 80% -h 75% "lazygit"

  ctrl-b ctrl-g will open a popup window with lazygit
  q to quit

https://huggingface.co/blog/fine-tune-whisper

https://github.com/unslothai/unsloth

I'm not sure if it contains exactly what you're looking for, but it includes several resources and notebooks related to fine-tuning LLMs (including LoRA) that I found useful.

Thanks! I really missed yahoo's :rofl: emoji

My experience has been just the opposite. We have moved all our apps to Elixir now. It has one of the best developer experience to work with. Especially for concurrent programming.

I suspect OP is using an umbrella app as a shared library or something. That is the only explanation I can think of that can cause the issue with compilation order.

About documentation, not quite sure what the OP is talking about. Elixir and Erlang have really good documentation.

Anyway, to truly appreciate Elixir (and for that matter Erlang), one needs to understand OTP and the philosophy behind it. It is not just a language but a framework to build concurrent application.

please do explain why

..but things like macros in Ecto....

Well, The whole language itself is built on macros. The following series of articles certainly helped me stop worrying and love the macros..

https://www.theerlangelist.com/article/macros_1

Some interesting insights from the article: "Elixir itself is heavily powered by macros. Many constructs, such as defmodule, def, if, unless, and even defmacro[1] are actually macros...."

[1] https://github.com/elixir-lang/elixir/blob/v1.18.2/lib/elixi...

You may be interested in watching this from the same author where he compares various IDEs including Cursor.

Addy Osmani – The Ai-Assisted Developer Workflow: Build Faster and Smarter Today https://www.youtube.com/watch?v=SpKtpW9TGF0

Highly recommend listening to In our Times (BBC) episode "The Habitability of Planets" that was aired last month.

https://www.bbc.co.uk/programmes/m0025vvd

I have been using it for more than a year now in both production and at home. So far so good. Even GPU works out of the box in rootless mode without requiring any special privileges. edit: Redhat in production and Debian at home

Do try it. We use it for text search in one of our apps and works remarkably well. Basically to find which chunks contain the given text. Since the text can span multiple chunks, a simple string search will not work.

Instead of doing a diff, curious if Normalized compression distance (NCD)[1] will yield a better result. It is very simple algorithm:

to compare two images, i1 and i2

  l1  = length(gzip(i1))
  l2  = length(gzip(i2))
  l12 = length(gzip(concatenate(i1, i2))

  ncd = (l12 - min(l1, l2))/max(l1, l2)

https://yieldthought.com/post/95722882055/machine-learning-t...

From the article:

"Basically it states that the degree of similarity between two objects can be approximated by the degree to which you can better compress them by concatenating them into one object rather than compressing them individually."

[1] https://en.wikipedia.org/wiki/Normalized_compression_distanc...

Thanks for that link!

There is another video posted 7 months ago from Seth where he interviews Ken Stanley, the creator of the NEAT algorithm.

https://www.youtube.com/watch?v=5zg_5hg8Ydo