zlacker

>>embedd+(OP)
What kind of time frame do you ballpark this would have taken you on your own?

I know it's a little apples-and-oranges (you and the agent wouldn't produce the exact same thing), but I'm not asking because I'm interested in the man-hour savings. Rather, I want to get a perspective on what kind of expertise went into the guidance (without having to read all the guidance and be familiar with browser implementation myself). "How long this would have taken the author" seems like one possible proxy for "how much pre-existing experience went into this agent's guidance".

>>happyt+ES1
I have a fun little tool which runs the year-2000-era sloccount algorithm (which is Perl and C so I run it in WebAssembly) to estimate the time and cost of a project here: https://tools.simonwillison.net/sloccount

If you paste https://github.com/embedding-shapes/one-agent-one-browser into the "GitHub Repository" tab it estimates 4.58 person-years and $618,599 by year-2000 standards, or 5.61 years and $1,381,079 according to my very non-trustworthy 2025 estimate upgrade.

>>simonw+GU1
I pasted a subset of the Fil-C source code into your tool and it says 6 person years. I just pasted the compiler pass and the obvious parts of the runtime.

Note that I started the project in Nov 2023 and can only work on it maybe 1-2 hours a day because it's just a side project.

So I think your tool either estimates based on very bad programmers, or it's just wrong. Or maybe 10x programmers are real and I am him

>>pizlon+YU2
Here's more about the COCOMO model it uses: https://dwheeler.com/sloccount/sloccount.html#cocomo

>>simonw+N33
Sounds like nonsensical pseudoscience

>>pizlon+I43
I don't take those results very seriously myself, but have you seen anything better?

>>simonw+Yq4
No

To me this is a case where knowing that you don't have data is better than having data and pretending it means anything