DoS007
DoS007
> Just chiming in, I've tried using v3-turbo for streaming and found that it hallucinates more/misses audio more than other faster-whisper models. For example for this 10 second audio clip...
Just like to add: Via playground on openai the websearch works, but it's different to chatgpt search at least for o3 and o4-mini. O3 web search with big context (specifically...
@enricoros Ah, ok (am using an own instance via vercel). I assume option one is only for a single page (but maybe possible for more using google api for search)....
Easy switching for reasoning or websearch is relevant (didn't test new github repo changes). _Include reasoning and websearch in message author name_: I also think, that knowing which answer was...
@enricoros > Should the prompt only be used for the current text (append or replace) or somewhere else? - Current prompt text box (in my version it has the same...
Isn't `\[` and `\]` for block latex and `\(` for `\)` for inline latex used these days? On the other hand it's sonnet 3.7 and not some "unrelevant" ai. Maybe...
@enricoros Maybe this is interesting for other people reading (or referencing for them): ## Data structure code location As I understand it's about [https://github.com/enricoros/big-AGI/tree/v2-dev/src/common/stores/chat](https://github.com/enricoros/big-AGI/tree/v2-dev/src/common/stores/chat)? A while ago it looked like...
@tfriedel @enricoros Keep alive implementation propose: **LastRequest** : The request that was used to get the newest ai-answer which is shown in chat. **Process/flow** : Roughly 4min48sec after the latest...
@enricoros To add another idea: Tapping on the middle screen to make the bottom and top bar shrink away (and *tapping again to access it again*).
@enricoros Hi, just saw https://github.com/enricoros/big-AGI/pull/798#issuecomment-3286970770 . What is the new sync system using? On app.big-agi.com I see a login need for google (I find google very privacy unfriendly), hopefully you...