Here mostly to read news.
Vancouver, BC, Canada
Joined March 2014
- Tweets117
- Following174
- Followers21
- Likes691
Yurko retweeted
Elixir v1.20 released! Now officially a gradually typed language: Elixir type checks every single line of code, finding bugs and dead code, without developer overhead (no typing signatures) and extremely low false positives rate. Plus a faster compiler! Links and reports below.
New Qwen 3.5 lineup is nothing short of breakthrough!
Genuinely impressed with coherence, knowledge and skill that are available on consumer hardware courtesy of @JustinLin610 and the team. All the best in your next adventure!
Below are some fun 27b replies.
Qwen3 4b VL is unexpectedly good for its size (trying it out in LM Studio) - so far it was able to count people in the picture (15), OCR verbatim, read and transcribe the table of data in Ukrainian - impressive!
Just started playing with #cometbrowser - feels very nice so far. Asked it to write a tune on strudel.cc - and it did fairly well :) perplexity.ai/search/open-st…
Yurko retweeted
Introducing ElixirPack, and swift-erlang-actor-system
github.com/otp-interop
#ElixirLang
Yurko retweeted
The Expert Language Server is live: github.com/elixir-lang/exper… - nightly builds available for alpha testing and contributors.
Thank you to @flydotio, @_tauspace_, and @River for sponsoring the development so far!
Yurko retweeted
these two days we are sharing the instruct and thinking models of our smaller variant of the 2507 seires, 30a3-2507. fast, but much smarter than before. i like this size, it is just something that i can easily play with, which is also somehow smart enough.
btw, i hope we can shoot coder 30a3 tmr.
🚀 Qwen3-30B-A3B-Thinking-2507, a medium-size model that can think!
• Nice performance on reasoning tasks, including math, science, code & beyond
• Good at tool use, competitive with larger models
• Native support of 256K-token context, extendable to 1M
Qwen Chat: Go to chat.qwen.ai/?model=Qwen3-30… and click “Thinking”.
HF:huggingface.co/Qwen/Qwen3-30… or huggingface.co/Qwen/Qwen3-30…
ModelScope: modelscope.cn/models/Qwen/Qw… or modelscope.cn/models/Qwen/Qw…
Yurko retweeted
We need a way to validate approaches to how we work with LLMs to write code, and we need to start developing the dataset. I've laid some groundwork here, but I need help. Tear it up, critique it, but most of all, PR some evals y'all. #MyElixirStatus github.com/ash-project/evals
Yurko retweeted
🎉 ElixirConf US speakers announced! @polvalente(Nx), @hugobarauna (Livebook/@Dashbit), Adam Kirk (Jump CTO), Michael St Clair (PDQ), @georgeguimaraes (ex-@plataformatec), @RezKate (Evirts). Early Bird ends in 2 days! ⏰elixirconf.com/#keynotes
Phoenix.new – The Remote AI Runtime for Phoenix fly.io/blog/phoenix-new-the-… via @flydotio
Exciting times :)
Yurko retweeted
Elixir 1.19 is a banger! I'm so pleased with the direction that #ElixirLang is going. My programs just get faster and more correct every time. I just know that we're in good hands. Thank you to everyone on the team for your hard work!
github.com/elixir-lang/elixi…
#MyElixirStatus
Yurko retweeted
Nice to see Apple is hiring Elixir devs and, apparently, they’re using Phoenix LiveView too:
jobs.apple.com/en-us/details…
Yurko retweeted
We are launching testnet with the pre-training of a 40B parameter LLM:
- MLA Architecture
- Dataset consisting of FineWeb (14T) + FineWeb-2 minus some less common languages (4T), and The Stack v2 (1T)
The resulting model will be small enough to train on with a single H/DGX and run on a 3090, but it will be powerful enough to serve as the basis for strong reasoning models and creative pursuits. The model will be trained continually without a final "annealing" step, resulting in a true unaltered base model.
Looking ahead, we will draw model ideas from the community via our forum and Discord. By enabling highly parallel and scalable experimentation, we’re betting that the next innovation in model creation and design will come from the open source community.
Yurko retweeted
I've just released Handoff, a new Elixir library for distributed function graph execution.
hexdocs.pm/handoff
Among other things, the library enables distributed Nx computations (anyone said distributed inference?)
A huge part of this was sponsored by @tvlabs!
Yurko retweeted
We created our own LLM evaluation test suite using ExUnit in @Learning_Elixir 😉 Want to know how? 🧵
#myelixirstatus
Yurko retweeted
Zed agents are officially out! Here is a video of me using Zed agents (during the beta) with Tidewave to "vibe code" the pricing plan component, all the way to database migrations.
This week's technology is amazing! Trying tidewave.ai with
@Alibaba_Qwen
3 4B as the "brains" of the operation - works out of the box. Just scratching the surface and excited about what I am seeing so far! As a bonus - puts my 3060 through paces. #myelixirstatus