Believe the Checkbook • Hacker News Board

Re: Believe the Checkbook

#81

Post by saghm » Sun, Dec 21, 2025, 1:50 AM UTC

lolc wrote: post #79

RealityVoid wrote: post #78

Earlier quoted context omitted.

> I explain to them that typing speed is never the bottleneck in the work that I do. Never is a very strong word. I'm not a terribly fast typist but I intentionally trained to be faster because at times I wanted to whip out some stuff and the thought of typing it all out just annoyed me since it took too long. I think typing speed matters and saying it doesn't is a lie. At the very least if you have a faster baseline…

An often repeated point on this forum: A lot of our comms are text. You don't want stall and lose attention to comms. Makes sense to train and have the flow on auto.

I've never had an issue where communication with my team has been hindered due to my typing speed not being high enough. If anything, I've been in plenty of text-based communications where it might have been beneficial for everyone to slow down a bit in how quickly they were sending messages in favor of more thoughtfully reading through everything before responding.

Re: Believe the Checkbook

#82

Post by faxmeyourcode » Wed, Dec 31, 2025, 7:22 AM UTC

maccard wrote: post #42

faxmeyourcode wrote: post #28

While I agree with the premise of the article, even if it was a bit shallow, this claim made at the beginning is also still true: > Everyone’s heard the line: “AI will write all the code; engineering as you know it is finished.” Software engineering pre-LLMs will never, ever come back. Lots of folks are not understanding that. What we're doing at the end of 2025 looks so much different than what we were doing at the…

Does it? I use AI as a smart auto complete - I’ve tried multiple tools on multiple models and I still _regularlt_ have it dump absolute nonsense into my editor - in thr best case it’s gone on a tangent, but in the most common case it’s assumed something (often times directly contradicting what I’ve asked it to do), gone with it, and lost the plot along the way. Of course when I correct it it says “you’re right, X doe…

Unfortunately this is a skill issue. And it's a totally different skill than reading and writing code, building solid systems, and general software engineering at large. That is annoying, but where we're currently at.

Assume you're writing code manually, and you personally make a mistake. It's often worthwhile to create a mechanism that prevents that class of mistake from cropping up again. Adding better LSP or refactoring support to your editor, better syntax highlighting, better type checking, etc.

That same exact game of whack a mole now has to be done for you and whatever agent you're building with. Some questions to ask: What caused the hallucination? Did you have the agent lay out its plan before it writes any code? Ask you questions and iterate on a spec before implementation? Have you given it all of the necessary tools, test harnesses, and context it needs to complete a request that you've made to it? How do you automate this so that it's impossible for these pieces to be missing for the next request? Are you using the right model for the task at hand?

Re: Believe the Checkbook

#83

Post by faxmeyourcode » Wed, Dec 31, 2025, 7:25 AM UTC

bonesss wrote: post #70

geitir wrote: post #64

Earlier quoted context omitted.

When you have that hair raising “am I crazy why are people touting ai” feeling, it’s good to look at their profile. Oftentimes they’re caught up in some ai play. Also it’s good to remember yc has heavy investment in gen ai so this site is heavily biased

Context is king, too: in greenfield startups where you care little about maintenance and can accept redundant front end frameworks and backend languages? I believe agent swarms can poop out a lot lot lot of code relatively quick… Copy and paste is faster though. Downloading a repo is very quick. In startups I’ve competed against companies with 10x and 100x the resources and manpower on the same systems we were buildi…

I use claude exclusively at my day job with legacy codebases. I'm not using swarms or fancy multi-agent setups. Just sticking to plan mode, giving enough context, and iterating on a spec before starting the actual build.

I'm also not building webapps. I work in data engineering on a large legacy airflow project, internal python libraries, infrastructure with terraform, etc.