@jipe_ia De bons conseils ! Par contre, petit correction technique... Que ce soit Anthropic, ou en local avec vLLM et Ollama, les serveurs de LLM optimisent ça par défaut aujourd'hui grâce au Prompt Caching (et au KV cache), pour éviter de cramer le budget ou faire ramer le serveur local.
Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor.
It’s happening faster than we thought, and the implications deserve greater attention. https://t.co/OVVPJO7VQx
shitting on our NATO allies for a year or more, Trump affect surprise when they won’t rush to our aid. It’s not like he consulted them before going to war with Iran.
Pragmatically, we can say that AGI is reached when it's no longer easy to come up with problems that regular people can solve (with no prior training) and that are infeasible for AI models. Right now it's still easy to come up with such problems, so we don't have AGI.
We are super proud to announce that Roguecraft is released!
It would not have been possible without support from the Amiga community. Thank you!🥳
Get the game here while it is 20% off. and let us know what you think: 🕹️
https://t.co/TSRQ4diOwQ
#amiga#roguelike#retrogaming
@SFR@REDbySFR
Bonjour SFR ! Trouvez-vous normal qu'un de vos techniciens débranche ma voisine suite au rebranchement de ma fibre et falsifie (!) ma signature sur le rapport d'intervention ?