As always, when you try to analyze the capabilities of these models, please look at the datasets they’ve been trained on! https://
x.com/hahahahohohe/s
/hahahahohohe/status/1765435151817830834
…
LLMS
-
Analyzing AI Model Capabilities Through Training Data Examination
By
–
-
New precision tuning feature launched for Gemini web app
By
–
A better way to tune the Gemini web app’s responses What: We’re launching a more precise way for you to tune Gemini’s responses. Starting in English in the Gemini web app, just select the portion of text you want to change, give Gemini some instruction, and get an output that’s
-
Google Gemini receives a new model update
By
–
BREAKING: A retro Gemini update from 04.03.24 came out being visible today Yesterday it was a blank placeholder.
-
LangChain Course: Functions, Tools and Agents Now Available
By
–
Check out our latest course with @DeepLearningAI on @coursera – Functions, Tools and Agents with LangChain. The landscape of LLMs and the libraries that support them has evolved rapidly in recent months. The course is designed to keep you ahead of these changes! You’ll
-
Claude vs GPT: Document Retrieval Behavior Differences
By
–
Another interesting thing that Claude does compared to GPT: each time you ask a question over a chat with provided docs, it always does the retrieval part, instead you need to force GPT into doing it for each message, and sometimes it just won't do it.
-
Discussion on AI model release expectations and naming
By
–
Rather that “smth new already came” and ppl have access to it to some extent. They could be rolling out ADA2 but it is not GPT-5 😛
-
Claude 3 Demonstrates Higher IQ Than Competing AI Models
By
–
I would also say (and forgive me for not having the data here) that Claude 3 has a higher IQ too, from what I have seen than any other models. I would say probably around 100.
-
Long Context and Memory Enhance AI Understanding
By
–
Long context, together with almost perfect retrieval and memory, would do that, plus sprinkle in a good level of understanding.
-
Improving LLM Testing Methodology Through Feedback
By
–
Appreciate the feedback. I'm taking notes so I can make future LLM tests even more thorough. 🙂