[verdverm]

these are trivial steps you can add in any script, as your link demonstrates.

Why would I want to add all this extra stuff just for that? The opaque retry until it returns valid JSON? That sounds like it will make for many pleasant support cases or issues

Personally, I have found investing more effort in the actual prompt engineering improves success rates and reduces the need to retry with an appended error message. Especially helpful are input/output pairs (i.e. few-shot) and while we haven't tried it yet, I imagine fine-tuning and distillation would improve the situation even more

[bwestergard]

There are many subtleties to invoking the typescript type checker from node. It's nice to have support for that from the team that maintains the type checker.

[smrq]

Admittedly, couldn't they spend some effort on making that invocation less subtle instead?

[verdverm]

Is the team working on typescript in a good position to be making LLM libraries, interfaces, and abstractions? Do they have the background and context to understand how their library fits into AI workflows? Could they have provided the same value with a blog post and sample code?

[icholy]

Your coworkers must love you.

[verdverm]

Indeed, we all do what we are good at and appreciate each other and no having to do the things they do

But what does your comment have to do with any of this at all?

[icholy]

It's called sarcasm. But here, let me say the same thing directly: you are an insufferable prick. Imagine gatekeeping talking to a fucking chatbot.

[verdverm]

If this is how you talk to people, it is quite clear who the bigger prick is, you don't even know me to make such judgements, rather shallow don't you think?

[behnamoh]

agreed. not to mention we're talking about Microsoft here. the same company that gave us "guidance", a defunct LLM framework.

[layoric]

I’ve used guidance, why is it defunct? I found it was powerful at templating, really decent for generating synthetic datasets.