This security flaw should be addressed, some GPTs still seems to be affected, but not @levelsio NomadGPT at least.
AGENTS
-
AI System Performance Issues and User Expectations
By
–
Can you please solve your current issues with not functioning as promised? Browsing the web for everything, using code interpreter to translate simple text. I miss the real you
-
All-in-One Model Automatically Selects Tools Without User Input
By
–
No not the tool selector, the fact that it picks for you in the new All-in-one model
-
User seeks direct conversation with Turbo AI model interface
By
–
Not the same. I want to talk to Turbo, like i can in the playground.
-
AI Should Understand Intent Without Constant User Interaction
By
–
Totally agree. I just don’t want to constantly be touching it. Feels like an uneccesary step. Should just know my intent
-
Creating a Custom GPT for Product Mockups
By
–
I made my first GPT via GPT Builder by @OpenAI
. ChatGPT is by far the best AI out there, no matter what anyone says. Feel free to create your product mockups via the link below: https://
chat.openai.com/g/g-ObnTYhLV2-
gpt-product-designer-by-god-of-prompt
… #GPTs #GPTBuilder #ChatGPT #ChatGPT4 #ChatGPT账号 #gpt4turbo -
Custom Instructions Cause AI Agent Web Browsing Regression
By
–
Yeah, I had to add a custom instruction and tell it to never browse the internet. Big regression
-
GPT-4 Router: Smart Tool Selection for AI Tasks
By
–
So there is some little helper, some part of the GPT4 interface that decides what underlying version of GPT4 is going to be used. If it should browse the web, use code-interpreter or DALLE-3 something that dictates what tools best used for the job, and currently that alignment
-
AI Assistant Mode Selection Issues Affecting Output Quality
By
–
Yeah, I mean don't get me wrong, the speed of the inference output is in many ways heaps better. But the fact that I'm constantly getting the browser mode or the data analysis mode, even tho Its not required or simply makes the output worse. Is not great.
-
Correcting PDF docs lacking full examples with manual instructions
By
–
Mine didn’t work well from PDF docs because there’s no full example on a single page (URL) — e.g. the Assistant tutorial never does `client = OpenAi()`. I just stuffed corrections of observed failures into the instructions. It only queries the KB for obscure stuff now.