41–50 of 137 posts
Is this an attempt to engender developer goodwill that they've lost over 5.2s overfitting issues? I've canceled my subscription, I don't plan on releasing an app to their platform.
What I really want from Anthropic, Gemini, and ChatGPT is for users to be able to log in with them, using their tokens. Then you can have open/free apps that don’t require the developer to track usage or burn through tons of tokens to demonstrate value. Most users aren’t going to manage API keys, know that that even means, or accept the friction.
I'm interested to see which companies and industries are willing to put ChatGPT between them and their customers, and how many will strongly push back against this feature.
Tried the GitHub app, made sure everything was properly connected, and asked a question about one of my repositories. It repeatedly claimed (5 times) that it wasn't connected and couldn't do anything, telling me to check the checkboxes that were already checked. Only after I showed it a screenshot of the settings did it suddenly comply and answer the question. I guess it still needs more polish.
Screenshots use a different router, so if you get stuck in one modality then pasting a screenshot can sometimes divert whatever "expert" you were stuck on that was refusing to comply. I don't work at OpenAI but I know enough about how these systems are architected to know that once you are stuck in a refusal basin the only way is to start a new session or figure out how to get routed to another node in their MoE conf…
In effect this means user input is easily disbelieved, and the model can accidentally output itself into a state of uncorrectable wrongness. By invoking the image tool, you managed to get your information into the context as “high veracity”.
Note: This info is the result of experimentation, not confirmed by anyone at OpenAI.
> Apps extend ChatGPT conversations by bringing in new context and letting users take actions like order groceries, turn an outline into a slide deck, or search for an apartment. Between this description and their guidelines these don't really sound like "apps", but a way to integrate an existing app with ChatGPT sessions. I'm trying to figure out what's in it for the developer other than ultimately taking users away…
> Apps extend ChatGPT conversations by bringing in new context and letting users take actions like order groceries, turn an outline into a slide deck, or search for an apartment. Between this description and their guidelines these don't really sound like "apps", but a way to integrate an existing app with ChatGPT sessions. I'm trying to figure out what's in it for the developer other than ultimately taking users away…
Since then, I’ve seen some very impressive demos and I’m excited to see what developers create on the platform as that’s always the coolest part.
Earlier quoted context omitted.
Screenshots use a different router, so if you get stuck in one modality then pasting a screenshot can sometimes divert whatever "expert" you were stuck on that was refusing to comply. I don't work at OpenAI but I know enough about how these systems are architected to know that once you are stuck in a refusal basin the only way is to start a new session or figure out how to get routed to another node in their MoE conf…
It’s actually more complicated than that now. You don’t get that kind of refusal purely from MoE. OpenAI models use a fine-tuned model on a token-based system, where every interaction is wrapped as a “tool call” with some source attached, and a veracity associated with the source. OpenAI tools have high veracity, users have low veracity. To mitigate prompt injection, models are expect a token early in the flow, and t…
Maybe an ad based system coming soon?