Joined February 2009
- Tweets 33,168
- Following 567
- Followers 732
- Likes 4,375
2,021 Photos and videos
Pinned Tweet
29 Sep 2024
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=oW91h8jF…
1
1
1
705
Valentin retweeted
Apr 23
New version of llmfit (github.com/AlexsJones/llmfit) today that supports Qwen3.6 models
1
4
461
Valentin retweeted
Apr 22
Qwen3.6-27B can now run locally! 💜
Run on 18GB RAM via Unsloth Dynamic GGUFs.
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs: huggingface.co/unsloth/Qwen3…
Guide: unsloth.ai/docs/models/qwen3…
Apr 22
🚀 Meet Qwen3.6-27B, our latest dense, open-source model, packing flagship-level coding power!
Yes, 27B, and Qwen3.6-27B punches way above its weight. 👇
What's new:
🧠 Outstanding agentic coding — surpasses Qwen3.5-397B-A17B across all major coding benchmarks
💡 Strong reasoning across text & multimodal tasks
🔄 Supports thinking & non-thinking modes
✅ Apache 2.0 — fully open, fully yours
Smaller model. Bigger results. Community's favorite. ❤️
We can't wait to see what you build with Qwen3.6-27B! 👀
🔗👇
Blog: qwen.ai/blog?id=qwen3.6-27b
Qwen Studio: chat.qwen.ai/?models=qwen3.6…
Github: github.com/QwenLM/Qwen3.6
Hugging Face:
huggingface.co/Qwen/Qwen3.6-…
huggingface.co/Qwen/Qwen3.6-…
ModelScope:
modelscope.cn/models/Qwen/Qw…
modelscope.cn/models/Qwen/Qw…
93
409
3,380
576,018
Valentin retweeted
Mar 31
Claude code source code has been leaked via a map file in their npm registry!
Code: pub-aea8527898604c1bbb12468b…
3,329
7,538
48,503
35,673,329
Valentin retweeted
Mar 24
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
307
2,242
9,331
5,850,294
Valentin retweeted
Mar 5
From the Macbook Neo video
301
735
17,152
1,686,665
Valentin retweeted
Feb 6
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 !
3
7
18
3,891
OWASP : TOP 10 des risques LLM et GenAI, édition 2025 programmez.com/actualites/ow…
1
96
Valentin retweeted
4 Apr 2025
Votre IA est brillante 🧠, mais est-elle vraiment connectée à VOTRE réalité d'entreprise ? 🤔 Les LLM génériques peinent souvent à accéder aux données et outils internes qui comptent VRAIMENT. #IA #EntrepriseTech 1/9
1
4
3
498
Valentin retweeted
18 Oct 2024
Une faille critique a été découverte dans l'outil de construction d'images Kubernetes, affectant la sécurité des déploiements dans le cloud.
👉 À lire sur The register : theregister.com/2024/10/16/c…
29
36
4,959
🚨 The .io domain, and all the associated websites might disappear
Last week, the UK announced the transfer of sovereignty over the Chagos Islands to Mauritius, which could spell the end of the .io domain.
But what does this mean? Let’s dive in! 🧵👇
2
6
9
4,136
29 Sep 2024
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=oW91h8jF…
1
1
1
705
29 Sep 2024
C'est de l'IA donc « c'est perfectible » (surtout avec un aussi petit modèle), mais l'expérience est intéressante.
1
107
Valentin retweeted
13 May 2024
Introducing GPT-4o, our new model which can reason across text, audio, and video in real time.
It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):
833
4,726
21,761
4,358,914
Valentin retweeted
13 May 2024
GPT-4o is INSANE 🤯
“Her” is becoming reality right now
78
343
2,768
540,579
Valentin retweeted
4 Apr 2024
C'est l'heure de mettre à jour PHPStorm avec la nouvelle version 2024.1 !
🖥️ Nouveau terminal (va peut-être remplacer @warpdotdev dans mon quotidien)
🚀 Code completion en local avec IA
🪲 Prise en charge de PHPUnit 11
🪲 Amélioration de la prise en charge de @pestphp
etc...
ALT Screenshot indiquant la possibilité de mettre à jour PHPStorm et les plug-ins.
2
3
5
1,211
4 Apr 2024
“Full Line Code Completion in JetBrains IDEs: All You Need to Know”
blog.jetbrains.com/blog/2024…
#local #ai @jetbrains
1
149
Valentin retweeted
4 Apr 2024
Home Assistant (68k stars) migrated to uv. They now save over five hours of execution time on each build...
ALT Arch | pip | uv | Savings aarch64 | 1h 24m 53s | 5m 18s | ~1h 20m armhf | 1h 52m 20s | 6m 2s | ~1h 46m armv7 | 1h 26m 43s | 5m 28s | ~1h 21m amd64 | 22m 10s | 3m 20s | ~19m i386 | 17m 37s | 3m 11s | ~14m
18
81
1,164
215,462