ChatGPT keeps polishing a new GPT-3.5 model called "text-davinci-002-render-paid" with vision capabilities. Currently, only a tooltip is available which hints: "Use photos to choose an outfit or analyze complex documents. Chatting about people in images isn't supported." Like
LLMS
-
User reports issues with ChatGPT file upload functionality
By
–
Even if enabled, the model itself is not available yet (at least for me). The upload button works but ChatGPT refuses to work with uploaded files for now.
-
LLMs Demonstrate Creative Capabilities Across Novel Complex Tasks
By
–
I would add that by every measure of creativity we have (all of which are flawed, which didn't matter when we were only measuring humans) LLMs produce creative results And frontier LLMs operate on a high level on novel managerial, medical, and legal tasks. Its all kind of weird.
-
DSPy and LangChain LLM Systems Optimization Webinar
By
–
Webinar: Optimization of LLM Systems with DSPy and LangChain/LangSmith Sign up here: https://
us06web.zoom.us/webinar/regist
er/WN_n4HUNqhFQFa4ax3kYrZW8g#/registration
… There are a lot of novel and interesting ideas in DSPy around optimization of LLM systems Super excited to host a webinar with Omar K. and
@hwchase17 diving into -
AI understands console formatting without library installation
By
–
Hahah true! It's interesting because if you ask it to run or execute, it says it can't or just provides an answer to the goal! I am just mind blown it understands the console formatting without having the library installed to do that
-
Insights on potential dynamic rate limits for GPT-4
By
–
I think they are planing to make rate limits dynamic so they will only kick in if the system is under a heavy load or similar conditions. Here is a new description under GPT-4 saying that “Usage limits may apply “. This feature is under A/B testing or internal testing at this
-
Claude executes code through framework simulation capability
By
–
I made a pretty interesting discovery.
— Pietro Schirano (@skirano) 26 mars 2024
If you paste the code for my framework, Maestro, into Claude and ask it to "simulate" a run, it will basically execute the code until it's done with the goal.
Claude will basically execute runs for any code you throw at it. pic.twitter.com/ndwzKsmNBaI made a pretty interesting discovery. If you paste the code for my framework, Maestro, into Claude and ask it to "simulate" a run, it will basically execute the code until it's done with the goal. Claude will basically execute runs for any code you throw at it.
-
Optimizing ChatGPT Response Quality via Custom Instructions
By
–
3. Add the following Custom Instruction to the "How would you like ChatGPT to respond?" field: #Professional/Semi-Formal Tone
#Length: Highest Verbosity Required
#Responses: Detailed, thorough, in-depth, complex, sophisticated, accurate, factual, thoughtful, nuanced answers w/ -
Improving ChatGPT Output Quality Through Prompting
By
–
4. Enjoy 10x better output with ChatGPT! You can edit some of them to personalize it further to your needs 🙂 I instantly noticed my ChatGPT responses became better.
-
Custom Instruction for Enhanced ChatGPT Prompting
By
–
2. Add the following Custom Instruction to the "What would you like ChatGPT to know about you to provide better responses?" field: # *IMPORTANT + DIRECTLY RELATED!*:{
The following is ALWAYS relevant
ALL queries = VERY Complex & Require HIGH Stakes Processing—I believe in you!