Вот теперь как белый человек могу просить локальную модель сделать рисерч.
Щас еще добавлю в свою openwebui агентов mistral (за 18 евро включены лимит на 25.5 евро API вызовов разных моделей), сделаю knowledge и будет у меня полноценный local LLM.
Yo @MistralAI it would be very nice of you if you could add a function to report bugs in your app.
My keyboard is gone every time I bring app from background and start a new chat. It’s 100% hit, not so hard to reproduce.
damirca retweeted
Elixir is very good at handling many connections without breaking. So you don't need to give it any special attention for good performance. Here a benchmark with a lot of clients posting to the once-campfire repos. Elixir mops the floor with the Rust versions.
Replying to @CaesarDavid_ @dhh
The problem with all of this that keeps getting glossed over is that Elixir is requiring all of this special attention to get it to the numbers it can achieve. I also believe those numbers under represent Elixir's potential but this isn't a "which is fastest" benchmark. It is "which is fastest without knowing how to write in that stack" benchmark.
Replying to @sami3dat
@sami3dat не могу перестать думать об этой машинке как основу для будущего LLM сервера вместо условной студии м5 за 6-7к ebay.de/itm/960000800685











