[have-a-break]

Honestly at work LLMs seemed to make me less productive. For side projects they help but I've seen papers indicating this is the case for industry.

We as engineers have let the recruiters and VC funding brainwash us into lower salaries. Kind of looking forward to a rebound.

[rednafi]

This is my experience too. All these LLMs and agents are great for bootstrapping projects faster than ever. They help immensely with bringing down the activation energy. So I do a lot more tinkering around in multiple languages that I wouldn’t have otherwise.

That said, once the project goes beyond a certain threshold, LLMs offer little more than a highly capable autocomplete. In larger codebases, the current context window is too small for the tools to even answer questions properly, let alone make any non-trivial changes.

Productivity starts going down once you try to use LLMs in a large codebase and expect them to be as helpful as they were in a smaller one. Often, these authoritative little shits will whirl you around in a doom loop and still won’t find any useful solution. And suddenly you find yourself having to clean up the mess.

I’d still say the productivity benefit is positive, but at the same time, the hype around these is bonkers. Employers are holding onto the hype cycle to bring down wages through FUD.

[roncesvalles]

>Productivity starts going down once you try to use LLMs in a large codebase and expect them to be as helpful as they were in a smaller one.

Exactly this. I've really tried to find use for LLMs in my big tech company SWE job and I just can't. The context is just too large, and not just the code context. In the time that I can "explain" everything to the LLM, keep iterating until it spits out something semi-useful and massage that into something I can merge, I'd rather just do the whole thing myself.

But it's amazing for greenfield personal projects.

[bluefirebrand]

> LLMs offer little more than a highly capable autocomplete

I find LLM autocomplete extremely annoying compared to traditional intellisense

It is wrong way more and I don't want multi-line autocomplete, it's too intrusive

[GardenLetter27]

Are you using Copilot or Cursor? I find Cursor's one pretty good. Although they just butchered their pricing :(

[bluefirebrand]

Cursor

It's more or less the same as intellisense most of the time, but occasionally it tries to guess an entire multi-line function and it throws me way off

I don't know if it's a matter of just sticking with it to learn like any new tool, or if it is just really not as useful as people say

One thing I've noticed is that with traditional intellisense it was often fast enough to get ahead of me so I could tab complete

Cursor is slower than me. Often I am typing faster than it can think, which makes it suggest things I'm already past.

[casualscience]

You need to setup the problem for the llm. If I am getting an error, I can normally piece together the 10k lines of relevant code much more quickly than I can track down the bug.

Llms are still a big speed boost there

[roncesvalles]

If you see an error and can't immediately Cmd+Shift+F an error code or something and jump to the exact line of code that threw the error, that's an engineering problem.

[JonChesterfield]

I'm decently excited about the new world of hugely increased quantity of terrible code. Not absolutely sure how to go mining yet but it has opportunity written all over it.

[9rx]

> Honestly at work LLMs seemed to make me less productive.

Significantly so! But the thrill of the gamble keeps me coming back, sadly.