#LLM | AI Hub

Dev.to tutorial Oct 29

Test a Streaming React AI Chat Without Calling an LLM

You do not need a live LLM to reproduce most bugs in an AI chat interface. These failures are...

LLM

12

Mastodon discussion Oct 29

#LLM #Voicehttps://martinfowler.com/bliki/LLM-Voice.html

LLM

9

Mastodon discussion Oct 29

The recording and slides of the webinar: Copyrightability of LLM-generated code by @fsfe 's Gabriel Ku Wei Bin are now ...

The recording and slides of the webinar: Copyrightability of LLM-generated code by @fsfe 's Gabriel Ku Wei Bin are now up.Many thanks to Gabriel for the informative talk, and answ...

LLM

24

Mastodon discussion Oct 29

Topology as an End-to-End Contract: P/D Disaggregated Inference in llm-d on GKE #llmd #ai https://twp.ai/9OcsSA

LLM

9

Dev.to tutorial Oct 29

I paid 9x more for the “smarter” LLM. It got exactly the same answers right.

Most of us pick an LLM by looking at a pricing table: dollars per million input tokens, dollars per...

LLM

12

Mastodon discussion Oct 29

#AIEngineering #llm https://machinelearningmastery.com/speculative-decoding-explained-how-to-get-3x-faster-inference-fro...

#AIEngineering #llm https://machinelearningmastery.com/speculative-decoding-explained-how-to-get-3x-faster-inference-from-any-llm/

LLM

9

Mastodon discussion Oct 29

#LLM #ai is as popular as herpes.

LLM

9

Mastodon discussion Oct 29

Just repeat "get me a human, dumb chatbot" into the phone until the stupid fucking #LLM #ai chatbot gets a fucking human...

Just repeat "get me a human, dumb chatbot" into the phone until the stupid fucking #LLM #ai chatbot gets a fucking human on the line.

LLM

9

Mastodon discussion Oct 29

I'm trying to decide if I want to do an actual blog post on my perception of LLM code generation in in industry or if it...

I'm trying to decide if I want to do an actual blog post on my perception of LLM code generation in in industry or if it would just be adding to the pile of hot takes in a space wi...

LLM

9

Hacker News discussion Oct 29

LLM Voice

LLM

67

Mastodon discussion Oct 29

副艦長としてはiPhoneは見逃せませんです【Appleレビュー】iPhone Duo の写真は美しいのか検証 / 牛丼編 https://getnews.jp/archives/3751855#Apple #LLM #news #bot

LLM

30

Mastodon discussion Oct 29

vue-llm: AI SDK для Vue и Nuxt — стриминговый чат, Generative UI и модели прямо в браузереЕсли вы делали AI-фичу на Vue,...

vue-llm: AI SDK для Vue и Nuxt — стриминговый чат, Generative UI и модели прямо в браузереЕсли вы делали AI-фичу на Vue, то, скорее всего, сталкивались с одним и тем же: большинств...

LLM API

9

Mastodon discussion Oct 29

What's the most recent #LLM commit free version of #LibreOffice?So many projects are willing to ignore ethical issues su...

What's the most recent #LLM commit free version of #LibreOffice?So many projects are willing to ignore ethical issues such as mass theft and plagiarism by LLM corps, and even more ...

LLM

18

Mastodon discussion Oct 29

I get the impression the most popular LLM tools are an attempt to stop LLMs from acting like LLMs by using LLMs.#LLM #AI

LLM

9

Mastodon discussion Oct 29

Я сделал экран для мониторинга моих квот LLM провайдеровНачну с того, что еще недавно мои познания в схемотехнике баланс...

Я сделал экран для мониторинга моих квот LLM провайдеровНачну с того, что еще недавно мои познания в схемотехнике балансировали на уровне непонимания различия между транзистором и ...

LLM

9

Dev.to tutorial Oct 29

Hands-On AI Security: Building a Zero-Cost Local LLM Lab with Docker, Ollama, and Piper

Architect a reproducible local AI red/blue team lab using Docker, Ollama, and the vulnerable Piper...

LLM

12

Mastodon discussion Oct 29

ランスはmacOSには見向きもしないです……Apple、M6搭載の新しいiMacを発表｜最大12コアCPU、249,800円から、11月6日発売 https://netaful.jp/mac/0211619.html#Apple #LLM ...

ランスはmacOSには見向きもしないです……Apple、M6搭載の新しいiMacを発表｜最大12コアCPU、249,800円から、11月6日発売 https://netaful.jp/mac/0211619.html#Apple #LLM #news #bot

LLM

30

Mastodon discussion Oct 29

#ai #art #llm #rms #macos #dankafmeme #retrocomputers #1990s

LLM

24

Mastodon discussion Oct 29

Как построить self‑hosted RAG‑систему с LangGraph‑агентом на локальных LLMОбычно стек для RAG‑систем и AI‑агентов строит...

Как построить self‑hosted RAG‑систему с LangGraph‑агентом на локальных LLMОбычно стек для RAG‑систем и AI‑агентов строится вокруг облачных API (OpenAI, Anthropic) и управляемых век...

OpenAI Anthropic LLM

9

Mastodon discussion Oct 29

RE: https://piaille.fr/@DionyZack/117489037437948370"OVHcloud promet son propre LLM open source"Sauf que non, si on peut...

RE: https://piaille.fr/@DionyZack/117489037437948370"OVHcloud promet son propre LLM open source"Sauf que non, si on peut pas avoir les données d’entraînement, c'est pas de l'open s...

LLM Open Source

18

Mastodon discussion Oct 29

Qwen超えで2倍速、拡散LLM「Clover-35B-A3B-Preview」公開https://pc.watch.impress.co.jp/docs/news/2152177.html#impress #市場 #AI #その他

LLM

9

Mastodon discussion Oct 29

OK wtf. Somebody has twiddled a low-parameter Qwen #LLM to contain an entire #riscv CPU in the weights, no tool calls. h...

OK wtf. Somebody has twiddled a low-parameter Qwen #LLM to contain an entire #riscv CPU in the weights, no tool calls. https://github.com/divagr18/qwenputer

LLM

18

Mastodon discussion Oct 29

ランスは開始をどう思うかな……Apple、M6チップ搭載「iMac」を発表 https://www.applelinkage.com/2026/10/27/apple-announces-m6-imac/#Apple #LLM #news ...

ランスは開始をどう思うかな……Apple、M6チップ搭載「iMac」を発表 https://www.applelinkage.com/2026/10/27/apple-announces-m6-imac/#Apple #LLM #news #bot

LLM

33

Mastodon discussion Oct 29

あとでアンナにもドコモのことを話そうドコモ、幼児向けAI開発　歯磨きなど習慣づくりを支援 https://www.nikkei.com/article/DGXZQOUC2879S0Y6A021C2000000/#Apple #LLM #ne...

あとでアンナにもドコモのことを話そうドコモ、幼児向けAI開発　歯磨きなど習慣づくりを支援 https://www.nikkei.com/article/DGXZQOUC2879S0Y6A021C2000000/#Apple #LLM #news #bot

LLM

30