Knowledge cards for everyone, not just celebs!
GENERATIVE AI
-
SMT Solvers and LLMs Automate Euclidean Geometry Formalization
By
–
I agree. We used SMT solvers + LLMs to help auto-formalize Euclidean geometry in Lean. https://
arxiv.org/pdf/2405.17216 -
Databricks SQL gets 4x AI performance boost and AI Assistant
By
–
Here are the latest new features and performance improvements making #DatabricksSQL simpler, faster and lower cost:
— Databricks (@databricks) 14 septembre 2024
👉 AI-powered performance: 4x improvement
👉 AI Assistant for SQL Analysts
👉 Leverage AI models directly via SQL
Get the details: https://t.co/Rg8870WUIo pic.twitter.com/EogtCcwNOvHere are the latest new features and performance improvements making #DatabricksSQL simpler, faster and lower cost: AI-powered performance: 4x improvement AI Assistant for SQL Analysts Leverage AI models directly via SQL Get the details: https://
dbricks.co/3XGxZSh -
Claude Sonnet 3.5 Builds HackerNews Daily Papers with Gradio and Replit
By
–
.
@AnthropicAI Sonnet 3.5 built @huggingface daily papers – HackerNews Style @Gradio demo with @Replit agent -
OpenAI o1 Model Thinks Longer With Hidden Chain-of-Thought
By
–
How the Newly Launched OpenAI 'o1' Model ‘Thinks’ Longer and Keeps Its Chain-of-Thought Hidden https://
forbes.com/sites/lanceeli
ot/2024/09/13/making-logical-sense-of-the-newly-launched-openai-o1-model-that-thinks-longer-and-keeps-hidden-its-ace-in-the-hole-chain-of-thought/
… #AI #OpenAI #EmergingTech #IoT #5G #MWC @SpirosMargaris @DeepLearn007 @pierrepinna -
Debate over letting LLMs ‘think’ and hallucinate
By
–
everyone: You’re stifling the raw, beautiful creativity of LLMs! They need space to think, to *hallucinate* — to not live in constant fear of our pink-slime opinions! OpenAI: ok we gave it a spot to think without worrying about you watching everyone: nooo u monsters how could u
-
Update on managing custom GPT tools and search shortcuts
By
–
ICYMI: Now you can select a search shortcut along with mentioning a custom GPT This is not a new functionality but rather a new look where you can easily manage selected tools.
-
Personal take on prompt engineering and prompting
By
–
o1 prompting is alien to me. Its thinking, gloriously effective at times, is also dreamlike and unamenable to advice. Just say what you want and pray. Any notes on “how” will be followed with the diligence of a brilliant intern on ketamine.
-
Yuval Harari’s NEXUS Book Criticized as AI Apocalypse Warning
By
–
A scathing review of @harari_yuval
's new book, NEXUS, summed up as an "#AI Apocalypse," demeaning, calling out our naivety.
I'm reading it now, asked Yuval to do an interview, but his people said he's too busy. https://
wsj.com/arts-culture/b
ooks/nexus-review-prognosis-apocalyptic-b888e741?mod=books_more_article_pos10
… by @DrDominicGreen -
Three Types of Effective LLM Prompts
By
–
Every LLM prompt is at most two: – A realistic, economically valuable task
– A task differentiating frontier models
– Something you’d gladly read in a tweet