Hacker News Reader

Comment by directevolve | Hacker News Reader

We’re already heading toward the sigmoid plateau. The GPT 3 to 4 shift was massive. Nothing since had touched that. I could easily go back to the models I was using 1-2 years ago with little impact on my work.

I don’t use RAG, and have no doubt the infrastructure for integrating AI into a large codebase has improved. But the base model powering the whole operation seems stuck.

View on HN

> I don’t use RAG, and have no doubt the infrastructure for integrating AI into a large codebase has improved

It really hasn't.

The problem is that a GenAI system needs to not only understand the large codebase but also the latest stable version of every transitive dependency it depends on. Which is typically in the order of hundreds or thousands.

Having it build a component with 10 year old, deprecated, CVE-riddled libraries is of limited use especially when libraries tend to be upgraded in interconnected waves. And so that component will likely not even work anyway.

I was assured that MCP was going to solve all of this but nope.

How did you think MCP was going to solve the issue of a large number of outdated dependencies?

Those large number of outdated dependencies are in the LLM "index" which can't be rapidly refreshed because of the training costs.

MCP would allow it to instead get this information at run-time from language servers, dependency repositories etc. But it hasn't proven to be effective.

> I could easily go back to the models I was using 1-2 years ago with little impact on my work.

I can't. GPT-4 was useless for me for software development. Claude 4 is not.

Interesting, what type of dev work do you do? Performance does vary widely across languages and domains.

Embedded software for robotics.

Reply on news.ycombinator.com