By
–
grok-2-latest 🤖 vs grok-3 🤖
— 🚨 AI News | TestingCatalog (@testingcatalog) 26 janvier 2025
What would you ask to impersonate who is who?
Drop your prompts below 👀 pic.twitter.com/JmgfREFPEV
grok-2-latest vs grok-3 What would you ask to impersonate who is who? Drop your prompts below
By
–
Kimi k1.5 got multimodal reasoning It guessed correctly that the city from where the graffiti is from. Loads of other use cases are supported!
By
–
provoking tips for prompting… have you tried anything like this? Do you think they actually work? #AI #ArtificialInteligence
By
–
I’ve learned more in 1 month with ChatGPT-4 than years of expensive courses. Here are 8 prompts that can save you thousands of dollars:
By
–
Reading the Deepseek-R1 paper today, here are some interesting bits that stood out for me: Prompting reasoning models like R1 is different: "Few-shot prompting consistently degrades its performance. Therefore, we recommend users directly describe the problem and specify the
By
–
O3-mini vs Gemini 2.0 Pro will be interesting. Lets see what will come on top
By
–
Perplexity released a reasoning toggle to let users select between normal Pro Search and Pro Search with Reasoning. Now you are in control
By
–
O1 Pro generates better writing, none of the AI slop of “seamlessly, effortlessly, …”. Good, on point, communication. But I wonder if this is just the training data, and less of the reasoning engine. Are we being upsold a less sloppy model?
By
–
Mistral rolled out a new feature called "schteumeul" which allows rendering markdown tables with Canvas.
— 🚨 AI News | TestingCatalog (@testingcatalog) 24 janvier 2025
There you can edit data, add or delete rows and apply different filters 👀 pic.twitter.com/Uck7PlKfXv
Mistral has released a new feature called 'schteumeul,' which enables rendering markdown tables using Canvas. With this feature, you can edit data, add or delete rows, and apply various filters.
By
–
no rag, but you can use r1 distills (the smaller ones)