LRMs — o1 models — and the new paradigm towards reasoningNotebook LM Podcast LinkOct 13, 2024Oct 13, 2024
LLama 3.2 — powerful small models for local use and multimodal diveWell, today was a hell of a day, between Mono and LLama 3.2, but in this post let’s compare LLama 3.2 with itself in previous iterations…Sep 26, 2024Sep 26, 2024
The AI RevolutionInformation is breaking it’s container again, now in the next level.Sep 12, 2024Sep 12, 2024
Where are we with in 2024 part 1 — RAG vs Long Context?Since 2022, things have been crazy. A lot of new or redefined concepts arrived and they seem to be constantly changing…Aug 18, 2024A response icon1Aug 18, 2024A response icon1
Gemini 1.5 Flash vs Gemini 1.5 Pro — How the model really performs?Google just released a very complete technical report of his new models including its performance compared to all of his previous ones…May 20, 2024May 20, 2024
Battle of the TOP — LLama 3, Claude 3, GPT4 Omni, Gemini 1.5 Pro-Light and moreSince everything seemed to calm down until the next second at least, let’s compare the latest TOP models considering multimodality…May 15, 2024A response icon1May 15, 2024A response icon1
GPT4 Omni — So much more than just a voice assistantToday we have the OpenAI Spring announcement and it was mind blowing, I guess we all can agree here. I was playing with my new voice…May 14, 2024A response icon1May 14, 2024A response icon1
RULER: Is your LLM using all his avaliable context?Since last year, many scientific papers have been released analyzing this aspect.May 12, 2024May 12, 2024
How to make MVP AI Projects with LLMs for free (for Devs)This is a guide of some alternatives we have if we want to make some AI MVP, a simple project or just try out without investing money to…Apr 3, 2024Apr 3, 2024
Gemini 1.5 Pro — API release date & Pricing Preview/Comparison Other ModelsGoogle started to announce (finally!!) a release date for Gemini 1.5 Pro API on Google Studio AI (no mention for VertexAI but I guess once…Apr 2, 2024A response icon1Apr 2, 2024A response icon1
