I've been evaluating OpenAI (GPT-3.5 and -4o) for a project at my company and I have seen differences in quality between the api and the web version as well. Same prompts. The api version seems to vary a lot more in quality.
It's not just that. Following instructions, text generation, etc. all seem to be worse with the api version. At least, when it comes to 3.5 - 4o is much better. Ironically, 4o had problems with correct json output where 3.5 hadn't. It produced ```json {...}``` instead of just the json object.
Yeah, I don’t know why their API is inferior to the UI. Pretty disappointing. I’ve had better luck with my own “clone” that makes a web search and summarizes the results into an answer.
I asked the time and it is 6 days late: I wrote about the delay and it says I may be pregnant
please note that this is not a free service
but, most of all, who wrote the bot? who will read what you write there? where is the privacy page? the EU privacy regulation ecc ecc?
the web page is not Telegram owned, and the
https://www.telegrambots.ai/privacy-policy I read there does not formal enough to me.... plus,... how can they offer you to add your bot, and at the same time have that privacy policy ? they control the code of my bot ? that "verified" sounds not formal too..
if it is an experiment fine... but it does not looks like it is
The money is in the app layer and compute. There's no reason to train foundation models to compete with Anthropic, OpenAI, Meta ect ect. Its the equivalent of lighting money on fire.
It worked better in the UI, I only had it with the API.