Valentin

33.2K posts

Valentin

@c4software

Dev Web et prof d’info, créateur de framework et de librairies en tous genres. Keyboard lover ⌨️🥰 https://t.co/wv0eZR2R0l

P4X-639 Tham gia Şubat 2009

565 Đang theo dõi735 Người theo dõi

Tweet ghim

Valentin@c4software·29 Eyl

Petite expérimentation de l'après-midi, intégration d'un système de « réécriture / résumer » via LLM dans mes supports de cours. Évidemment, l'intégration est « On Device » pour utiliser #llama 3.2 3B. L'utilisation de #WebLLM est vraiment très simple ! youtube.com/watch?v=oW91h8…

YouTube

Français

658

Valentin đã retweet

Daniel Hnyk@hnykda·2d

LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server + self-replicate. link below

English

302

2.3K

9.4K

5.5M

Valentin đã retweet

Marques Brownlee@MKBHD·5 Mar

From the Macbook Neo video

English

312

753

17.4K

1.7M

Valentin@c4software·5 Mar

@XKamidh Moi, c'est pas mal je trouve.

Français

Baptiste PROVOOST@XKamidh·5 Mar

Qui utilise vraiment la fonction Desk View d'Apple ? support.apple.com/fr-fr/121541

Français

100

Valentin@c4software·5 Mar

@ssamat Nice feature, working great here, but it would be great to have an option like in Dex to make the phone act as a touchpad.

English

Sameer Samat@ssamat·5 Mar

Popular request! Looking forward to feedback on Desktop Mode.

Mishaal Rahman@MishaalRahman

🖥Super excited to see Desktop mode finally launch! With the release of Android 16 QPR3 today, connected display support has reached general availability. This means you don't need to flip a Developer option to enable it - just connect a compatible Android device to an external display via USB-C, and you'll get a desktop-like multitasking experience! It's one of many new awesome features in the latest Android release, but it's one I've been looking forward to a ton. Can't wait to see its evolution!

English

369

15.9K

Valentin@c4software·3 Mar

@digitalix Hey! Question I’m running a 36GB M3 Pro dedicated to AI, but I’m experiencing pretty slow prompt processing (especially with OpenCode and Claude). I’m considering upgrading my setup. Would you recommend going with an AI MAX 365+ or moving to an M4 Pro/Max instead?

English

104

Valentin@c4software·27 Şub

@ollama Is your mail support working? I wrote an email a few weeks ago and got no answer.

English

Valentin@c4software·27 Şub

@ollama @Steven_Soto And it's now available !

English

Valentin@c4software·27 Şub

@ollama @Steven_Soto Do you know when this version will be available with Brew ?

English

ollama@ollama·26 Şub

Ollama now supports vision capabilities in OpenClaw ollama launch openclaw --model kimi-k2.5:cloud OpenClaw can now see images, read screenshots, and extract details from photos

English

550

32.9K

Valentin@c4software·26 Şub

@ollama @Steven_Soto Yes, but for now it's giving a 500 error with the 0.17 version (unsupported model architecture)

English

ollama@ollama·26 Şub

@Steven_Soto It's there since the launch! ollama run qwen3.5:35b ollama run qwen3.5:122b ollama.com/library/qwen3.5

English

211

Valentin@c4software·11 Şub

@ollama @Zai_org Thanks for the quick answer. Meanwhile I sent you a DM, if you have time to look at it.

English

112

ollama@ollama·11 Şub

@c4software @Zai_org really by use case; here are some targeted use cases that we are mainly addressing

English

766

ollama@ollama·11 Şub

❤️ GLM-5 is on Ollama's cloud! It's free to start, and with higher limits available on the paid plans. ollama run glm-5:cloud It's fast. You can connect it to Claude Code, Codex, OpenCode, OpenClaw via ollama launch! Claude: ollama launch claude --model glm-5:cloud Codex: ollama launch codex --model glm-5:cloud

Z.ai@Zai_org

Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5, it scales from 355B params (32B active) to 744B (40B active), with pre-training data growing from 23T to 28.5T tokens. Try it now: chat.z.ai Weights: huggingface.co/zai-org/GLM-5 Tech Blog: z.ai/blog/glm-5 OpenRouter (Previously Pony Alpha): openrouter.ai/z-ai/glm-5 Rolling out from Coding Plan Max users: z.ai/subscribe

English

176

1.8K

178K

Valentin@c4software·9 Şub

@YaLTeRz Okay, NVM, I rebooted it. It seems okay now 🤔

English

YaLTeR@YaLTeRz·9 Şub

@c4software This rule applies specifically for when you're targeting an individual window with a screencast, i.e. not a full monitor cast

English

Valentin@c4software·9 Şub

@YaLTeRz I having an issue with the is-window-cast-target=true match need something specific ? I tried using the sharing feature of Chrome. But my rules are not applied (I use the one from the documentation)

English

Valentin@c4software·9 Şub

@YaLTeRz Yep, but it seems broken, at least the window I picked did not have the is-window-cast-target at true.

English

Valentin đã retweet

Gonzague 👨🏼‍💻@gonzague·6 Şub

Since @DJIGlobal does not provide an API for integration of their expensive robots, @n0tsa started trying to find a way to make .. his own API. The idea? Being able to control the robot in systems like @home_assistant What he found? He can access all of DJI's robots in the world. Seeing their infos but also controlling them !

English

3.8K

Valentin@c4software·31 Oca

@ollama Hey, I sent you a DM. I don't know if you've seen it. Thanks in advance 😊.

English

Valentin@c4software·21 Oca

@gonzague @kristouf En mode sauvage (j'ai tourné plusieurs années comme ça, commande volet de velux solaire). L'avantage de la Tahoma mini c'est le retour d'état dans home assistant via homekit.

Français

130

Valentin@c4software·21 Oca

@gonzague @kristouf Je confirme, rien à l'horizon pour l'instant. En RTS, énormément de solutions existent. J'utilise un RFLink perso. Sinon, côté IO, pendant longtemps je tournais avec des télécommandes officielles pilotées via ESP. Maintenant, j'ai une Tahoma mini + bridge HomeKit sur HA.

Français

135

Gonzague 👨🏼‍💻@gonzague·21 Oca

🥲 ESPSomfy RTS in the house, l'alternative open source pour contrôler ses stores @Somfyfr !