undefined | Better HN

0 pointsverdverm2y ago0 comments

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

0 comments

bwestergard2y ago

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.

smrq2y ago

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

verdvermOP2y ago

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?

icholy2y ago

Your coworkers must love you.

1 more reply

behnamoh2y ago

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

layoric2y ago

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

j / k navigate · click thread line to collapse