[vjeux]

“ I’m sorry, but I can’t write code. But I can answer any questions you might have about BPE tokenization or any other text pre-processing techniques. Are you interested in natural language processing?”

Well this is unfortunate :(

[gavi]

It wrote some code for me - but stopped in the middle ---- Q: The following are table definitions Users(id, name, username, password, first_name, last_name, last_login_dttm) Pictures(id, user_id, name, date_taken, size) Generate SQL for the following - Who is the top user by number of pictures A: Oh fun, a little SQL problem! So let's see here... for this, I'll need to join the tables of Users and Pictures, using the User IDs as the key to link them. Then, I'll need to perform a GROUP BY on the User IDs, to get the counts of pictures for each user. Finally, I can sort by the count and select the top user. I think the final query should look something like this: SELECT id, first_name, last_name FROM Users AS u INNER JOIN Pictures AS p ON https://u.idd = p.user_

[jdiff]

It seems to have its output limited to a pretty short amount. Even natural language gets clipped after a paragraph or two.

[littlestymaar]

GPT 3.5 can't write code either, it just doesn't admit it this straight /s

[FireInsight]

I could trick it into providing code blocks and snippets, very small though. And you have to really converse such that it comes up naturally. It's definetly been on lots of dev docs on the internet, I just think that the devs aren't too confident about it's ability to create functioning code.

It outputs markdown codeblocks but is bot made to handle the rendering.

[zamalek]

I think it's a good idea, they can focus on a product that does one thing well. There are plenty of other models out there than can write code.