Hacker News Reader

Comment by sega_sai | Hacker News Reader

It seems there is a battle of two opposite view-points. One is that LLMs are just dumb autocompletes with no ability to understand anything. Another is that LLMs can already right now be substitutes for programmers. I personally thing it is neither, but for experts who know what they are doing it is a massive time saver. I.e. in cases you know what code you want to write, but it's tedious, LLMs can do for you. Also LLMs are great in cases where you are less familiar with a new API, language, but have generally good understanding of programming.

Despite my broadly positive view on usefulness of LLMs, I do not think they are good enough (yet) to build a full system from scratch without an expert supervisor. This should not IMO be used as a 'proof' they are dumb autocompleters.

View on HN

> I.e. in cases you know what code you want to write, but it's tedious, LLMs can do for you

I feel like I'm living on another planet when I see this point. I have almost never in my career encountered the situation where actually typing out the code is the time consuming part. The time consuming part is knowing what code you want to write, running it in a variety of circumstances to gain confidence that it's correct, and iterating when it isn't.

Please don't think I'm saying you're wrong by the way—if anything this just shows how diverse programming can be as a career. But I see this point raised a lot and it doesn't match my experience at all.

Experts who know what they are doing have long had alternatives beyond LLMs to make their work faster.

They have open source libraries, stack overflow, tutorials, documentation, simple code generator tools and snippets.

The speed up we’re seeing is from LLMs basically caching all those things into a huge mathematical model and retrieving information in summarized form ready for consumption.

And while speed is always nice, LLMs are expensive, require maintenance themselves to maintain relevant context, are still error prone, and terrible at true innovation.

In a few years we’ll be talking about the big “AI crash” and “what went wrong” when it has been obvious to experts all along. Winter is coming.

I am sorry, but the comparison of 'stack overflow' and tutorials to LLMs is bizarre. The amount of time to get to the answer from LLMs is drastically shorter. And claiming that the they only 'cache thing' is just wrong. They are certainly capable of correctly answering things that were not directly in their training set.

Do you have any examples of a question you could ask to an AI right now that you couldn’t find from a basic search on stack overflow and Google? Didn’t think so.

Reply on news.ycombinator.com