With any serious LLM library, it takes one line to change the core model.
@dfintelligence
-
@dfintelligence — 2026-06-27
By
–
ATTENTION !!!! Ce serait une très grave erreur de se priver des modèles open source chinois ultra-performants en France. Des réponses orientées ou biaisées, oui, il y en a. Oui, il y en aura. Il y en en a aussi chez Mistral AI, GPT, Anthropic, etc. La probabilité qu'un agent
-
Critique of Dario’s apocalyptic predictions and privatization of AI models
By
–
All of this is because of Dario, damn it, and his apocalyptic delusions. There. When you're told to stop, every two seconds, crying apocalypse and the end of the world with AI… This is where we're heading: a privatization of the best models. Bravo. GG. Thanks guys.
-
Errata: Brave integrated into DINUM Assistant with LLM and web search separation
By
–
ERRATA: Someone just explained to me that Brave is here called at the level of "The Assistant", the agent developed by DINUM. They separated the LLM model from web search queries in order to have more flexibility (which is smart and consistent, by the way). >>> So here, x.com/DFintelligence…
-
MistralAI uses Brave Search API, but more complex than claimed
By
–
ERRATA IN REPLY TWEET. I thought it was a joke, but yes, @MistralAI does use the Brave Search API for its web searches. However, it's a bit more complicated than what that mister over there wants us to believe. Brave Search does have a ZDR (Zero Data…
-
Testing the Unreal MCP this week: feedback and advice?
By
–
I've scheduled to test the Unreal MCP this week. Does anyone have feedback? Advice please?
-
Sarcasm on AI rejection by non-users
By
–
The less you use AI, the more you reject it? Oh well, how surprising indeed……..
-
Scepticism about 42% of French wanting an AI pause
By
–
Tell me this figure is fake please. How can 42% of French people want to pause AI? We will never learn from our mistakes.
-
Equivalent SOTA model, open access, not free, no third-party dependency
By
–
In fact, you have a model equivalent to SOTA models on many benchmarks, freely accessible, obviously not free because you have to account for the cost of hardware, but thus possibly without depending on a third-party actor. What is good when a new model comes out is to look at
-
Comparing models is not limited to pure performance
By
–
Comparing models is not just a matter of pure performance.