ChatGPT may let users select if they want to rewrite its response using web search or without. These options will be mutually exclusive. Looks like a good improvement
@testingcatalog
-
Improving Prompt Complexity for Better AI Results
By
–
Yes, my initial prompts were quite generic. I need to make them a bit more complex
-
The Impact of Compute Capacity on AI Model Usage and Economics
By
–
It’s interesting to observe how limited compute capacity impacts consumer behavior. I believe that in the future we will have more and more such cases as soon as models will advance further. Think of it as a weekly budget that you can decide how to distribute. At the current
-
Observations on o1 model search retrieval and writing style
By
–
I haven't run a lot of testing yet but here are some quick observations:
– Retrieving knowledge via search didn't change much – o1 blindly trusts the Bing search index unless you clarify your reasoning.
– Written outputs follow the same GPT writing style and are not "humanised" -
Using AI compute quotas for automated news publishing workflows
By
–
Do you also hoard your compute quota for o1 model and plan to utilize it on something really useful? I will invest it in news publishing workflows to evaluate its writing capabilities
-
ChatGPT UI update adds completion status indicators
By
–
ICYMI: ChatGPT shows blue dots on the conversation history in case you left the conversation before the response was finalised. These are notifications of completion
-
Using OpenAI o1 to humanize AI-generated content
By
–
Asking o1 to humanise the post it wrote previously. It was quite at a good level. I will publish some examples today
-
User experience with AI prompt efficacy
By
–
I have used only 4 messages so far. Planning to focus on more complex prompts for writing. So far it is hard to say. Only one of my 4 queries were good. But it is too little
-
User comparison of GPT-4o performance
By
–
Not much different from 4o in many of my use cases to be honest.