Hacker News Reader

Comment by inciampati | Hacker News Reader

Except: you can feed it an entire programming language manual, all the docs for all the modules you want to use, and _then_ it's stunningly good, whipping chatgpt4 that same 10x.

View on HN

I gather the pricing is $8 for a million input tokens [1] so if your language's manual is the size of a typical paperback novel, that'd be about $0.8 per question. And presumably you get to pay that if you ask any follow-up questions too.

Sounds like a kinda expensive way of doing things, to me.

[1] https://www-files.anthropic.com/production/images/model_pric...

From my perspective it sounds pretty cheap if we get to the answers immediately.

Have you tried it? GPT4 fails as often as it succeeds at coding questions I ask so I'm not going to shell out that kind of money to take my chances.

Claude? No, have requested access many times but radio silence.

OpenAI? I use ChatGPT A LOT for coding as some mixture of pair programmer and boilerplate, works generally well for me. On the API side use it heavily for other work and its more directed and have a very high acceptance rate.

If you need a lot of revisions/tweaks, the price could be pretty prohibitive.

Can you just tell it to focus on a particular language and have it go find the manuals? If it is so easy to add manuals, maybe they should just make options to do that for you.

How do you do this? Links / more info?

I honestly don’t have time for that level of prompt engineering. So, chatGPT wins (for me)

Yeah but if their model would be accessible it would already have good vscode extension

Right "may as well do it myself" - I think this is the natural limit these things will reach. Just my opinion.

Gpt4 has 128k context length now.

gpt4 turbo

Reply on news.ycombinator.com