it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ultra. oh agents? you do that in spark actually. no, not gemini api managed agents, that’s different. for coding use jules. unless you mean the agentic ide, that’s antigravity. no, that’s the old antigravity, download the new one. actually gemini cli is being deprecated, use antigravity cli. no the flash model is smarter than the pro model. unless you need pro. if it’s video, use flow. no, flow uses veo. no, nano banana is images. actually that’s in gemini now. unless you’re in search, then it’s ai mode. no, research is notebooklm. anyway it’s all very simple.
@leonpalafox Un modelo state of the art quizá no.
Usando un modelo híbrido que pase la voz a texto, procese con un LLM no tan caro y luego pase texto a voz sí podría salir más barato. Pero pierdes un poco de efectividad y buen juicio.
Not yet there.
ChatGPT image 2.0 is great but the only benchmark it cannot achieve is to create a picture of a left handed person writing
why is it so hard even for nano banana 2?
@realtadev @samuel_ferrero En el vídeo menciona que es buena estrategia agregar tus apuntes de obsidian y notebooks de NotebookLM a Gemini para complementar.
Seguro así obtienes esa información extra que mencionas.
@samuel_ferrero RESUMEN:
Usa obsidian para llevar un control de tus conocimientos.
Busca vídeos en YT (muchos) sobre lo que quieras aprender. No los veas, agrégalos a notebookLM (usa un plugin de chrome).
Pide a notebookLM que te explique lo que no sabes basándote en tus notas de obsidian.
@gabrielchua@OpenAIDevs why is OpenAI not updating their embedding models? Google just released the last SOTA of embedding models but OpenAI hasn’t launched any new model since 2024
@dejavucoder I don’t think so. Opus could be GPT pro and sonnet vanilla GPT.
Mini and specially nano have never been good models.
They’re always behind of even identical open weight models.