Yurko

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.

@steipete Out of curiosity- have you considered taskwarrior?

damn I should stop using markdown files in git

Classy move!

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 :) #0" target="_blank" rel="nofollow noopener">perplexity.ai/search/open-st…

@bcardarella You can also configure a fallback to a different provider (e.g AWS Bedrock) if Anthropic is down.

This is a serious question. Is there something I'm not obviously getting?

@NVIDIAGeForce GeForce Day

🟢 GEFORCE DAY IS BACK 🟢 To celebrate, we're giving away TWO GeForce RTX 5080 Founders Edition GPUs, signed by NVIDIA CEO Jensen Huang. Want one? Comment "GeForce Day" for a chance to WIN & stay tuned for more!

Excited to release a preview of Moondream 3. A 9B param, 2B active MoE vision language model that makes no compromises; offering state-of-the-art visual reasoning while still retaining an efficient and deployment-friendly form factor.

Introducing ElixirPack, and swift-erlang-actor-system github.com/otp-interop #ElixirLang

The Expert Language Server is live: github.com/elixir-lang/ex… - nightly builds available for alpha testing and contributors. Thank you to @flydotio, @_tauspace_, and @River for sponsoring the development so far!

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.

@ZachSDaniel1 I would suggest to try it out as a default shell. Very discoverable, good docs, was quite easy to pick up and use as daily driver. Never looked back to fish.

Should I learn nushell tho?

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/ev…

🎉 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! ⏰#keynotes" target="_blank" rel="nofollow noopener">elixirconf.com/#keynotes

Phoenix.new – The Remote AI Runtime for Phoenix fly.io/blog/phoenix-n… via @flydotio Exciting times :)

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/el… #MyElixirStatus

"I’m far more interested in using AI to enhance our productivity and our tools. If we’re reaching for the stars, why not aspire to make every developer a 10x developer?" - dashbit.co/blog/announcin…

Nice to see Apple is hiring Elixir devs and, apparently, they’re using Phoenix LiveView too: jobs.apple.com/en-us/details/…

@bcardarella I recommend trying out @nu_shell - great took all-around + great discoverability and nice readable errors out of the box.

With this temp laptop and no access to my original config files I need to rebuild my dev env. I was using zsh, what are the kids using today?

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.