News for hackers. Stuff that matters.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by inciampati on Tuesday November 21, 2023 @12:02PM (#38366398)
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.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by FrustratedMonky on Tuesday November 21, 2023 @12:17PM (#38366667)
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.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by cowthulhu on Tuesday November 21, 2023 @12:08PM (#38366496)
If you need a lot of revisions/tweaks, the price could be pretty prohibitive.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by chubot on Tuesday November 21, 2023 @12:14PM (#38366590)
How do you do this? Links / more info?
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by p1esk on Tuesday November 21, 2023 @12:06PM (#38366464)
Gpt4 has 128k context length now.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by whimsicalism on Tuesday November 21, 2023 @12:23PM (#38366787)
gpt4 turbo
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by davedx on Tuesday November 21, 2023 @12:04PM (#38366437)
I honestly don’t have time for that level of prompt engineering. So, chatGPT wins (for me)
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by machiaweliczny on Tuesday November 21, 2023 @12:06PM (#38366471)
Yeah but if their model would be accessible it would already have good vscode extension
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by roflyear on Tuesday November 21, 2023 @04:22PM (#38370378)
Right "may as well do it myself" - I think this is the natural limit these things will reach. Just my opinion.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by michaelt on Tuesday November 21, 2023 @12:24PM (#38366802)
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...

Re:Anthropic announces Claude 2.1 – 200k context, less refusals by infecto on Tuesday November 21, 2023 @12:40PM (#38366986)
From my perspective it sounds pretty cheap if we get to the answers immediately.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by esafak on Tuesday November 21, 2023 @01:07PM (#38367462)
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.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by infecto on Tuesday November 21, 2023 @05:42PM (#38371522)
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.