You can easily do this, at least with Claude Code. Ask it to install and use Playwright to confirm rendering and flow. You're correct that it is a failing to not do this. When you do, it definitely helps cut down on bugs.
EDIT: Sorry, just noticed you said "real browser". Haven't tried this but Playwright gets you a long way down the road.
Yes, as all of modern politics illustrates, once one has staked out a position on an issue it is far more important to stick to one's guns regardless of observations rather than update based on evidence.
And sometimes that advocacy is harmful, desperate, arrogant flailing—against the reality one knows is true with overwhelming likelihood—manifesting as "advocacy" or "will" that destroys so many chances for fully experiencing the reality of the precious, remaining, time one has (or one has with one's partner).
NOTE: This is not me disagreeing at all, just your point moved me to make the obvious counterpoint, having been through all this myself very literally and very recently. I know firsthand how important the advocacy is, but also how often it causes nothing but harm. There is a real tricky balance between agency vs acceptance when you've truly lost control of things, like in these cases.
Sure, and we probably all agree that these are personal decisions. If the OP wants to dedicate his life to working on this particular problem, great. Maybe he makes a meaningful contribution. Maybe he just helps his partner make better informed medical decisions. Even if you plan to follow standard of care, doctors often present choices that balance risk vs result.
Also, doctors split their time among patients and their various diseases. You, on the other hand, can focus your study on your disease. If you have a scientific mind, you can become an expert with enough study.
Good article! I especially liked the approach to replicate manual commits with the agent. I did not do that when learning but I suspect I'd have been much better off if I had.
It's not just a joke, it's a meta-joke! To address the substance of your comment, it's probably an opportunity cost thing. Programmers on staff were likely engaged in what was at least perceived as higher value work, and replacing the $250/mo subscription didn't clear the bar for cost/benefit.
Now with Claude, it's easy to make a quick and dirty tool to do this without derailing other efforts, so it gets done.
> Programmers on staff were likely engaged in what was at least perceived as higher value work, and replacing the $250/mo subscription didn't clear the bar for cost/benefit.
Agreed absolutely, but that's also what I'm talking about. It's very clear it was a bad tradeoff. Not only $250/month x three seats, but also apparently whatever the opportunity cost just of personnel tied up doing "2-3 files a day" when they could have been doing "2-3 files an hour".
Even if we take at face value that there are no "programmers" at this company (with an employee commenting on hacker news, someone using Claude to iterate on a GUI frontend for this converter, and apparently enough confidence in Claude's output to move their production system to it), there are a million people you could have hired over the last decade to throw together a file conversion utility.
And this happens all the time in companies where they don't realize which side of https://xkcd.com/1205/ they're on.
It's great if, like personal projects people never get started on, AI shoves them over the edge and gets them to do it, but we can also be honest that they were being pretty dumb for continually spending that money in the first place.
Yes, the problem of accurately measuring software "productivity" has stymied the entire industry for decades, but people keep trying. It's conceivable that you might be able to get some sort of more-usable metric out of some systematized AI analysis of code changes, which would be pretty ironic.
Did you ever play The Prisoner? Where you go to the psychiatrist and he asks you all these questions, then the BASIC program crashes and prints an error message like "SYNTAX ERROR IN LINE ####" and beeps, leaving you at the "]" prompt?
But it's really an AppleSoft Basic Prompt Simulation to see how you will deal with the program crashing, judging you on if you go "CONT" or "NEW" or "RUN" or "CATALOG" or "LIST ####"!
What I didn't realize until I just looked it up now:
>In Prisoner 2 (the 1982 remake of the original), the game intentionally simulates a crash by showing a “Syntax error in line ###” message where the line number is actually your secret resignation code. The idea is that you might try to inspect or debug that line and type in the code, thereby revealing it — which is a loss condition because the game’s entire goal is to not give that number up.
Personally I really enjoy the syntax of Inform 7, but tastes vary and I certainly understand not liking it.
TADS 3 is another option if you prefer a more object-oriented, ALGOL-ish syntax with equivalent power.
The IFComp has run for decades now. If you are interested in good adventures, running through the highly-rated games from over the years is a good idea.
Despite the false advertising in the Tears for Fears song, everybody does _not_ want to rule the world. Omohundro drives are a great philosophical thought experiment and it is certainly plausible to consider that they might apply to AI, but claiming as is common on LessWrong that unlimited power seeking is an inevitable consequence of a sufficiently intelligent system seems to be missing a few proof steps, and is opposed by the example of 99% of human beings.
EDIT: Sorry, just noticed you said "real browser". Haven't tried this but Playwright gets you a long way down the road.
reply