50 key questions explaining core LLM concepts, v/Hao Hoang: https://
bit.ly/45aq6Zn
GENERATIVE AI
-

50 Key Questions Explaining Core LLM Concepts
By
–
-
Recent AI Models Fall Short of Expectations in 2026
By
–
ok fair, i overstated a bit. but look the whole field though pure pretraining would do well and then in November many reports emerged saying that recent models like Orion (relabeled as 4.5) and Behemoth didn’t meet expectations. And GPT-5 still hasn’t emerged. Did that change
-
What Will AI Accomplish in Five Years That Seems Impossible Today?
By
–
Gauntlet thrown: What specific, testable things will AI be able to do in 5 years that are truly impressive yet not achievable now?
-
Doctor fears AI will control medical diagnoses and prescriptions
By
–
J’en suis désolé en tant que medecin
— Docteur Laurent Alexandre (@dr_l_alexandre) 15 juin 2025
Cela me fait peur pour ma profession
Mais dans quelques années on nous interdira de faire un diagnostic ou une ordonnance sans l’autorisation de l’Intelligence Artificielle
Quelle claque
Quelle blessure pic.twitter.com/MgfWb1mxegJ’en suis désolé en tant que medecin Cela me fait peur pour ma profession Mais dans quelques années on nous interdira de faire un diagnostic ou une ordonnance sans l’autorisation de l’Intelligence Artificielle Quelle claque Quelle blessure
-
Vanna: Open-Source RAG Framework for Text-to-SQL Generation
By
–
Text-to-SQL tool that actually works!
— Sumanth (@Sumanth_077) 15 juin 2025
Vanna is an open-source RAG framework for complex Text-to-SQL generation, designed for handling dynamic datasets.
It's 100% open-source pic.twitter.com/YFkRUrq4CiText-to-SQL tool that actually works! Vanna is an open-source RAG framework for complex Text-to-SQL generation, designed for handling dynamic datasets. It's 100% open-source
-
GithubSearchTool: RAG Access to GitHub Code
By
–
GithubSearchTool Give your agents access to GitHub and do RAG over code. Read more
-
LLMs as Savants: Memorization Versus Derivation Pain
By
–
Memorization is easier but less useful than thought, which is why memorization needs to be a more painful activity than derivation. Savants can be immune against this pain, and LLMs are savant AI.
-
LLMs Performance Degradation at Critical Thresholds
By
–
Yeah all LLMs suddenly become *extremely* dumb when you hit that point.