top | item 43684148

(no title)

forbiddenvoid | 10 months ago

It's definitely an issue. Even the simplest use case of "create React app with Vite and Tailwind" is broken with these models right now because they're not up to date.

discuss

order

lukev|10 months ago

Time to start moving back to Java & Spring.

100% backwards compatibility and well represented in 15 years worth of training data, hah.

speedgoose|10 months ago

Write once, run nowhere.

int_19h|10 months ago

Maybe LLMs will be the forcing function to finally slow down the crazy pace of changing (and breaking) things in JavaScript land.

yokto|10 months ago

Whenever an LLM struggles with a particular library version, I use Cursor Rules to auto-include migration information and that generally worked well enough in my cases.

tengbretson|10 months ago

A few weeks back I couldn't even get ChatGPT to output TypeScript code that correctly used the OpenAI SDK.

seuros|10 months ago

You should give it documentation is can't guess.

Zambyte|10 months ago

By "broken" you mean it doesn't use the latest and greatest hot trend, right? Or does it literally not work?

dbbk|10 months ago

Periodically I keep trying these coding models in Copilot and I have yet to have an experience where it produced working code with a pretty straightforward TypeScript codebase. Specifically, it cannot for the life of it produce working Drizzle code. It will hallucinate methods that don't exist despite throwing bright red type errors. Does it even check for TS errors?

taikahessu|10 months ago

It has been really frustrating learning Godot (or any new technology you are not familiar with) 4.4.x with GPT4o or even worse, with custom GPT which use older GPT4turbo.

As you are new in the field, it kinda doesn't make sense to pick an older version. It would be better if there was no data than incorrect data. You literally have to include the version number on every prompt and even that doesn't guarantee a right result! Sometimes I have to play truth or dare three times before we finally find the right names and instructions. Yes I have the version info on all custom information dialogs, but it is not as effective as including it in the prompt itself.

Searching the web feels like an on-going "I'm feeling lucky" mode. Anyway, I still happen to get some real insights from GPT4o, even though Gemini 2.5 Pro has proven far superior for larger and more difficult contexts / problems.

The best storytelling ideas have come from GPT 4.5. Looking forward to testing this new 4.1 as well.

alangibson|10 months ago

Try getting then to output Svelte 5 code...

division_by_0|10 months ago

Svelte 5 is the antidote to vibe coding.

asadm|10 months ago

usually enabling "Search" fixes it sometimes as they fetch the newer methods.