111–120 of 222 posts
EDIT: found the button, all the way down in the bottom of the page... I hate this so much, give me the original content, I will decide if and when I need translation
What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…
I've heard it said that measuring productivity of a software developer by lines of code added, is akin to measuring the productivity of an aerospace engineer by mass added. It is a metric. It is often not a good metric. But it is easy to measure.
What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…
I have also grown skeptical of token usage in order to run up my bill! But since I feel like it takes me MORE effort to write LESS lines of code myself, I'd expect a quick and dirty AI-generated solution to be MORE lines of code and cost LESS to generate than a concise/elegant solution in LESS lines of code.
What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…
Lines of code has always been a terrible metric. But all else being equal it is a measure. If all else is not equal, which is usually the case, then it's not. A lot of the focus has been on AI recently. Three years ago we didn't have software where a non-software engineer can describe what they want in English and get working (-ish) software generated by other software? Is that not "software has gotten a lot better"?…
That being said while I agree that measuring better quality of software is vague (part of the reason it is hard for models as well), there are universal things I believe every engineer will agree on. Reliability, uptime, customer feedback, legibility of your engineering, performance, these are things we often optimized for. Google Maps is a bit of a strawman because neither of us (unless you work on it), knows how much agent code there is, I think it is likely that it's little since it was working fine prior to 2023. I could bring up github reliability as an example, given how much copilot usage they promote at MS, but once again only folks there know for certain. I do, however, see scores of various AI powered SAAS that looks like it is in a perpetual MVP state. I think you are right in that even if agents give us "good enough" results and we can swallow failure rates and our increasingly lesser understanding of what we, or more so model, created, then it is still progress overall, but this is progress not to human-AI collaboration but to AI-only engineering IMO, this is good or bad depending on how you view the future.
I'm a scientist and most of code I currently write is somewhere on the intersection of critical software and machine learning, squaring these two is not easy and I guess the way I was taught to reason about engineering informs my opinions on this. Maybe it's just a matter of time before codex can help here in an unconstrained manner as well, but I am skeptical at the moment.
Earlier quoted context omitted.
I do quite a lot of what this post describes in a reasonably large project. Here's what works for me: - write gherkin features for new features; update them for enhancements; don't touch them for refactors. Label your PRs with these nouns. - use pre-push hooks for type checks, linting, unit tests, and other quick, scriptable validations. - make a viteperess subsite in your repo, have the agents maintain it - document…
Can you share your skill please?
I'm building a skill + CLI tool along those lines (for solo devs not corporates). Here is what my "lifecycle" type skill looks like right now: https://github.com/bitkentech/shipsmooth/blob/releases/dist/... (warning, heavily work in progress). You can see a demo here: https://shipsmooth.net/
I was not happy with the default code quality generated by Claude Code. So I've been adding some skill-file rules to address that, and so far happy with the results: https://github.com/bitkentech/shipsmooth/tree/main/skills/ex.... There was a similar one on HN yesterday called opencodereview: https://news.ycombinator.com/item?id=48406358
There are many such workflows out there! Matt Pocock gave a good talk about how he approaches it: https://www.youtube.com/watch?v=-QFHIoCo-Ko
Earlier quoted context omitted.
Can you share your skill please?
That's a big ask. This kind of harness usually contains plenty of proprietary insights about their business. And also, nowadays, a good harness is a major competitive advantage.
Also, a skill is not a harness.
I wish these breathless blog posts would actually try to be more didactic. For example, actually doing a walkthrough of how to set up these allegedly super powered workflows and concrete demonstrations. I’m not an AI skeptic. Rather I’d don’t want to miss out on any actual super powers.
1. What’s the job satisfaction like day to day being an engineer on this project? How have they adapted to this way of working?
2. How much did it cost? Work is being done whilst the engineers sleep but if that 6 hours overnight task cost $300 and could have been done by a person in 2 hours is it a real saving?