[flagged]
[flagged]
Agentic coding notes
91–99 of 99 posts
Re: Agentic coding notes
#92I'd like to highlight a different part of the article: > In general, when I talk to software folks about testing, I'm coming from such a different place that they immediately look at me like I'm an alien, so let's talk about how we tested at this hardware company I worked for, Centaur, which informs my biases about how I like to work. Some of the things that we did that were or are unorthodox in the software world ar…
No code review by default goes against actual established evidence (there is little of this for software development practice) that code review is the best way to find defects. I always get the impression from using hardware and other anecdotes like this that it is rare for hardware companies to know how to do software development well because their core competency is hardware. In fairness, it is uncommon for softwar…
What’s the established evidence?
Certainly it is very uncommon for to be reviewing a postmortem thinking ‘I wish we were more thorough with code review’ rather than ‘what changes to our testing practices could have increased our chances of catching this bug’. I don’t think the value of code review is normally in catching bugs.
Re: Agentic coding notes
#93Earlier quoted context omitted.
I'm saddened to have gotten this far and had my bubble burst, I legitimately thought someone was on the real GI's and was able to compose such a treatise, nevertheless.
You think humans consuming the Galápagos Islands is something worth aspiring to?
Its more that I had hoped that someone with clear AI psychosis was in the right place for them to step back from that precipice and that we might all learn something valuable from observing it.
Re: Agentic coding notes
#94Earlier quoted context omitted.
Every metric becomes a target (Goodhart's law). Also, the plural of anecdote is not data. The subjective anecdotes from HN users matter because they are not data and are much harder to game. Not impossible to game, always be aware of users with low karma, but more difficult than gaming a benchmark.
But they’re not at all meaningful after a certain point, because they’re not even attempting to explain why it works well for them. It’s just noise like this.
If somebody gives a longer explanation of why they like or dislike it that would just be more noise it doesn't really matter that much beyond their general opinion about it
Re: Agentic coding notes
#95Earlier quoted context omitted.
Toggle to "reader view" or resize your window. It is up to you and really isn't that hard.
"You can lead a horse to water, but you can't make him drink" Reader view makes the text too narrow: https://imgur.com/a/yQqzxco Sure i could take extra steps to make it more readable, but at that point I rather not read it as im not that interested nor invested. Totally fine, no complains from my side. But If the author wants to increase the reach of their posts they just might use agentic coding to have the llm opt…
"Reader view" is adjustable via your personal settings, so I am not sure what you are talking about.
Re: Agentic coding notes
#96A lot of the crazy ideas seem to have melted away in the face of massive context sizes. Today, I can put roughly a megabyte of utf8 text into my system prompt before things start to get weird. That is a massive amount of information even if we are being sloppy with it. You can read The Hobbit and the first Harry Potter book cover-to-cover and still have room to spare. I would deeply struggle to develop a world model…
[flagged]
Re: Agentic coding notes
#97Really interesting article but there's one thing I wanted to point out about the reasons for code review:
> If a company were shipping bugs at, say, a hundredth the rate we were at Centaur while relying primarily on review to catch bugs, then I could see their point, but that's not what's happening at the typical software company where people don't want to move away from human review [there might be non quality (as in non bug rate) related reasons to keep human review, such as keeping a high bar for code quality or keeping the codebase human-understandable, which pretty much immediately stops being the case if you let a fleet of agents go wild on a codebase] because of the perceived risk of shipping bugs.
I don't agree that the main point of a code review is quality assurance; there are other reasons that have more to do with team convergence and junior staff learning: https://www.embeddedrelated.com/showarticle/807.php
Re: Agentic coding notes
#98I've read a lot of comments about using AI for coding, and my experience has been very different.
I work on large C++ applications used by international airlines. If this software failed, it would make national headlines.
Claude Code with Opus 4.8 is great at handling the boring code I don't want to write myself. It gets it right almost every time.
However I still review every change and test everything before committing.
Trust, but verify.
Re: Agentic coding notes
#99[flagged]