Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Cool: Hugging Face is now supported in opencode, select your favorite model from the Hub and it will consume your inference quota directly. I recommend starting with GLM-4.5 (great at coding + awesome at agentic tasks)

victormustar's profile picture

Victor M

28,179 subscribers

50,554 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildungKunst
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

GLM-4.7 is supported in TRAE! You can plug in GLM-4.7 via as a custom model provider and run it directly in your agentic workflows.
0:10

GLM-4.7 is supported in TRAE! You can plug in GLM-4.7 via as a custom model provider and run it directly in your agentic workflows.

TRAE

21,571 Aufrufe • vor 7 Monaten

another open source win: opencode + GLM 4.6 is basically Claude Code (used it all day) but insanely cheap + better TUI. And you can use it with your Hugging Face token now 🔥
0:18

another open source win: opencode + GLM 4.6 is basically Claude Code (used it all day) but insanely cheap + better TUI. And you can use it with your Hugging Face token now 🔥

Victor M

217,717 Aufrufe • vor 10 Monaten

Hugging Face 🤝 Jan You can now use Hugging Face as a remote model provider in Jan. Go to Settings -> Model Providers -> add your Hugging Face API key. Then open a new chat and pick a model from Hugging Face. Works with any model in Hugging Face in Jan.
0:16

Hugging Face 🤝 Jan You can now use Hugging Face as a remote model provider in Jan. Go to Settings -> Model Providers -> add your Hugging Face API key. Then open a new chat and pick a model from Hugging Face. Works with any model in Hugging Face in Jan.

👋 Jan

22,264 Aufrufe • vor 1 Jahr

Use Your Private Models on Comfy Cloud! Continue client work safely — or generate with your experimental private models. You can now import models directly from private Hugging Face or Civitai repos. Just add your private key and model URL, and we will bring the models to your workflow! Everything you import stays 100% private to your account.
0:12

Use Your Private Models on Comfy Cloud! Continue client work safely — or generate with your experimental private models. You can now import models directly from private Hugging Face or Civitai repos. Just add your private key and model URL, and we will bring the models to your workflow! Everything you import stays 100% private to your account.

ComfyUI

17,705 Aufrufe • vor 6 Monaten

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun
0:11

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun

chiefofautism

341,710 Aufrufe • vor 6 Monaten

What if your model handled its own tuning? ⚙️ With NVIDIA TAO 7, just prompt your coding agent what you want in plain language and let it do the rest. • Agent skills plug into your coding agent and improve accuracy. • AutoML removes the guesswork from hyperparameters. LLM-guided tuning finds strong configs up to 2x faster. • Fine-tune any Hugging Face CV or VLM model on local NVIDIA GPUs. • Data enhanced fine-tuning helps your agent identify why the model fails, then fix it. Try TAO skills ➡️
0:12

What if your model handled its own tuning? ⚙️ With NVIDIA TAO 7, just prompt your coding agent what you want in plain language and let it do the rest. • Agent skills plug into your coding agent and improve accuracy. • AutoML removes the guesswork from hyperparameters. LLM-guided tuning finds strong configs up to 2x faster. • Fine-tune any Hugging Face CV or VLM model on local NVIDIA GPUs. • Data enhanced fine-tuning helps your agent identify why the model fails, then fix it. Try TAO skills ➡️

NVIDIA AI

41,902 Aufrufe • vor 1 Monat

NXT Live is at the Town Toyota Center in Wenatchee, WA TONIGHT! Get your tickets now starting at $25! See your favorite NXT Superstars live in action! 👏👏 Ticket Link:
0:17

NXT Live is at the Town Toyota Center in Wenatchee, WA TONIGHT! Get your tickets now starting at $25! See your favorite NXT Superstars live in action! 👏👏 Ticket Link:

Joe Hendry

19,546 Aufrufe • vor 6 Monaten

Introducing Hyperbridge Move your assets from any chain directly into Hyperliquid Starting with USDT0, USDe, PLUME, COOK, USR, and RLP Bridge now at powered by LayerZero
0:15

Introducing Hyperbridge Move your assets from any chain directly into Hyperliquid Starting with USDT0, USDe, PLUME, COOK, USR, and RLP Bridge now at powered by LayerZero

LayerZero

555,734 Aufrufe • vor 1 Jahr

Open weights just caught up to the frontier. GLM-5.2 from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.
0:18

Open weights just caught up to the frontier. GLM-5.2 from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.

CoreWeave

16,637 Aufrufe • vor 1 Monat

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇
0:15

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇

EyeingAI

40,960 Aufrufe • vor 5 Monaten

Smartest AI update for Chrome You can now use Gemini from anywhere: - Type "@" in the top bar - Select "Chat with Gemini" - Write your prompt next Press Enter and Chrome will answer you directly using Gemini! No longer need to open a new tab, access Gemini and then finally type your prompt. Everything is done directly from the top bar in one go: a huge productivity boost!
0:17

Smartest AI update for Chrome You can now use Gemini from anywhere: - Type "@" in the top bar - Select "Chat with Gemini" - Write your prompt next Press Enter and Chrome will answer you directly using Gemini! No longer need to open a new tab, access Gemini and then finally type your prompt. Everything is done directly from the top bar in one go: a huge productivity boost!

Paul Couvert

62,465 Aufrufe • vor 2 Jahren

Recently Theo - t3.gg told me "TANSTACK Start will be the future of full-stack JS" so we went ahead and integrated Tidewave with it. Give your favorite coding agent access to TanStack's server logs, let it detect and fix error pages, and drive UI changes directly from the browser!
0:19

Recently Theo - t3.gg told me "TANSTACK Start will be the future of full-stack JS" so we went ahead and integrated Tidewave with it. Give your favorite coding agent access to TanStack's server logs, let it detect and fix error pages, and drive UI changes directly from the browser!

José Valim

33,337 Aufrufe • vor 7 Monaten

AI NEWS: OpenAI just launched 'Tasks', allowing users to schedule actions and reminders within ChatGPT. Tasks can be one-time reminders or recurring actions (like a daily news rundown), with up to 10 active tasks able to be scheduled at a time. A new '4o with scheduled tasks' model will be available in the dropdown menu, and ChatGPT will also be able to suggest frequent tasks from a user's chat history. The beta feature is rolling out to Plus, Team, and Pro ChatGPT subscribers over the next few days. Is this the first (baby) step in ChatGPT's agentic era? 🤖
0:11

AI NEWS: OpenAI just launched 'Tasks', allowing users to schedule actions and reminders within ChatGPT. Tasks can be one-time reminders or recurring actions (like a daily news rundown), with up to 10 active tasks able to be scheduled at a time. A new '4o with scheduled tasks' model will be available in the dropdown menu, and ChatGPT will also be able to suggest frequent tasks from a user's chat history. The beta feature is rolling out to Plus, Team, and Pro ChatGPT subscribers over the next few days. Is this the first (baby) step in ChatGPT's agentic era? 🤖

Rowan Cheung

355,674 Aufrufe • vor 1 Jahr

Free for one week, exclusively in Nous Portal: Solar Pro 4, the new agentic model from Upstage, built to complete multi-step tasks across long documents and to recognize when it needs more information rather than inventing it. Try it today at
0:16

Free for one week, exclusively in Nous Portal: Solar Pro 4, the new agentic model from Upstage, built to complete multi-step tasks across long documents and to recognize when it needs more information rather than inventing it. Try it today at

Nous Research

198,215 Aufrufe • vor 4 Tagen

Kling 3.0 is now available in 4K on Higgsfield. Native output from the model, not upscaled in post. Generate ads, film, and broadcast-ready footage directly from your prompt.
0:16

Kling 3.0 is now available in 4K on Higgsfield. Native output from the model, not upscaled in post. Generate ads, film, and broadcast-ready footage directly from your prompt.

Higgsfield AI 🧩

141,762 Aufrufe • vor 3 Monaten

🚨🇨🇳 China's new coding model flawlessly outperforms its US rivals Zhipu AI's new flagship AI model GLM-5.2 has become the first Chinese model to rank in the top three globally on on front-end coding abilities 🔸 Users praise it as the first open-weight model reliable enough for daily coding workflows 🔸 It runs about 48% cheaper than US alternatives 🔸 It arrives as US labs face export restrictions and users fret over surging AI costs The model shows China is neck-and-neck with the US on AI performance — and now aims to overtake such giants as Anthropic and OpenAI
0:19

🚨🇨🇳 China's new coding model flawlessly outperforms its US rivals Zhipu AI's new flagship AI model GLM-5.2 has become the first Chinese model to rank in the top three globally on on front-end coding abilities 🔸 Users praise it as the first open-weight model reliable enough for daily coding workflows 🔸 It runs about 48% cheaper than US alternatives 🔸 It arrives as US labs face export restrictions and users fret over surging AI costs The model shows China is neck-and-neck with the US on AI performance — and now aims to overtake such giants as Anthropic and OpenAI

Sputnik

35,286 Aufrufe • vor 1 Monat

The Playtest Feature is BACK! Starting today, you can now move and practice with your character inside the select screen UI. We pioneered this in the original Rivals of Aether, and we're excited to bring it back
0:10

The Playtest Feature is BACK! Starting today, you can now move and practice with your character inside the select screen UI. We pioneered this in the original Rivals of Aether, and we're excited to bring it back

Rivals of Aether II

50,733 Aufrufe • vor 1 Jahr

So right now basically anyone with a 16GB VRAM card can go on Hugging Face and download a model which BEATS Claude Sonnet 4.5, all running locally 🤯 LOOK AT THE WATER PARTICLES?? What are they doing in these labs man What is this Unsloth AI UD quantization magic?? I'm running the lowest Q3 here, it oneshots everything 😭 Bros what is happening?
0:13

So right now basically anyone with a 16GB VRAM card can go on Hugging Face and download a model which BEATS Claude Sonnet 4.5, all running locally 🤯 LOOK AT THE WATER PARTICLES?? What are they doing in these labs man What is this Unsloth AI UD quantization magic?? I'm running the lowest Q3 here, it oneshots everything 😭 Bros what is happening?

left curve dev

90,204 Aufrufe • vor 3 Monaten

BREAKING 🚨: Google is preparing Gemini Agent prototype to perform your tasks on the web! It is likely to be powered by the recently released Computer User model and will be able to operate a browser and perform deep research. With great power comes responsibility 🤖
0:14

BREAKING 🚨: Google is preparing Gemini Agent prototype to perform your tasks on the web! It is likely to be powered by the recently released Computer User model and will be able to operate a browser and perform deep research. With great power comes responsibility 🤖

TestingCatalog News 🗞

119,790 Aufrufe • vor 10 Monaten