Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Anthropic’s Claude LLM is pretty interesting. In many ways it feels much more limited than GPT4. However, it is suspiciously good at a few edge-case code generation tasks (can’t go into details) that makes me wonder where it got its training data from. It also seems to be much less prone to hallucinating APIs and modules, preferring instead to switch back to natural language and describe the task without pretending it has a functioning solution handy.

Worth keeping an eye on for sure.



Didn't they partner with SourceGraph to make Cody? Here's them talking a bit about it: https://www.youtube.com/watch?v=LYuh-BdcOfw. Maybe that's why?


Anthropic actually uses a more cutting edge fine-tuning than OpenAI, a technique that doesn't rely on RLHF. Maybe this gives it an advantage in some areas even if their base model is only on the level of GPT-3.5 (used in free ChatGPT).


I know you said no details, but can you at least share a little bit more about Claude LLM's code generation?


There is a language with massive usage in the enterprise but with very few (if any) high quality code examples on the public internet.

When given a broad task, GPT4 doesn’t just write incorrect code, it tries to do entire categories of things the language literally cannot do because of the ecosystem it runs inside.

Claude does a much better job writing usable code, but more importantly it does NOT tell you to do things in code that need to be done out-of-band. In fact, it uses natural language to identify these areas and point you in the right direction.

If you dig into my profile & LinkedIn you can probably guess what language I’m talking about.


it’s just a language, why the mystery?


I feel like this could characterise anything by from COBOL to Java depending on how wry your smile was when you wrote it…


GPT4 has built and deployed an entire SaaS for me in a week. I already have users.

The edits required were minimal --- maybe one screw-up for every 100 lines of code --- and I learned a lot of better ways to do things.


Currently using GPT-4 to do a lot of heavy lifting for me for new app. Would love to see your approach!


I wrote it using a framework whose most recent release is substantially different than what GPT-4 was trained on.

I quickly learned to just paste the docs and examples from the new framework to GPT, telling it "this is how the API looks now" and it just worked.

It helped me do everything. From writing the code, to setting up SSL on nginx, to generating my DB schema, to getting my DB schema into the prod db (I don't use migration tooling).

Most of my time was spent telling GPT "sorry, that API is out of date --- use it like this, instead". Very rarely did GPT actually produce incorrect code or code that does the wrong thing.



This is incredible, thanks for sharing!


Which makes the “build vs buy” argument a whole lot more interesting.


Very interested was it CRUD? Are you building in public


Yes, essentially a CRUD wrapper for a specific domain of tech.


“I’ve got a secret!”

giggles and runs across the playground

In all seriousness, I downvoted your comments because they added little to the conversation. Congrats on being an insider.


It's Apex I assume. Salesforce's language.


That makes sense. My brother, who has been coding since 1990 and worked his entire career in boring Fortune 500 companies, was wholly unimpressed by chatGPT. It failed pretty miserably whenever he threw any old tech stack at it.


What about other tasks, like research in other areas? How is Claude different than chatGPT ?




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: