Viewing profile — aiunboxed

If your company has a microservice architecture but doesn't have proper knowledge on how should they communicate, how should they share code etc then it is the worst thing possible…

What do you use for tracing llm calls etc ?

Introduction on how node js implements parallelism using event loops and worker threads.

Is it working ? Historically speaking it has taken openai some time to stablise new features - gpt 4, browse plug-in.. let us see how this goes.

YouTube is used as Spotify in a India. I usually get 50 per cent of my music from YouTube and rest 50 from Spotify

Any way to find out function prompts as well. Let us say in Gpt plug-ins?

What would be great if these papers can also have some same prompts shared on github / share gpt so that everyone can try

And no ads in between of meditation videos No ads when you are driving - since you can't skip them

Also some questions - how much is the role of product vs distribution? - should be go aggressive on distribution with a relatively new product?

How does your image / video processing pipeline look like ?

It reminds me of how there was a dispute of X's logo being taken from a mono type font https://www.ft.com/content/da262b2a-f39a-466b-9b2f-2f8fa84f0...

Apple will probably just price the individual parts high by claiming that their parts are of higher quality which will again deter customers to get their parts repaired.

Hopefully Altman and Microsoft backend Helion can solve this problem. Excited to see the future of that company as well.

Agree, that is all kids would need.

Typescript, Python all are exception

This has always been a debate in my head whether to make the function return error codes or to throw those errors. Irrespective of throwing an error or returning an error you need …

It is back up

Hmm, hopefully people have enough avenues to match the extra income that they are going to generate

Yes right, and who doesn't like free publicity amongst their TG

Any reason why palm or cohere models are not here ?

I think pretty much all the companies who provide vector search are indirect competitors

:D :D Sorry my question was on the basis of the quality of the results, simply put .. how does players who have good semantic search turn out against "legacy" players who had good …

I wonder how do legacy search players like elastic / solr compete against the new age startups combining semantic and regular search ?