Does it yield good results? I found that instead of docs it’s easier just to ask ai to read code. I feel like this is same as comments in code. Become outdated fast

I don't really use "docs" for documentation. I've prompted Claude/Codex to always write a "log" and save it in-repo to track what it did and why.

I've found this to be really helpful, e.g. "you did this last week, and now some other thing is happening" or "you tried this approach before to solve alert X but it didn't work" -- except it can discover this itself.

https://github.com/shepherdjerred/monorepo/tree/main/package...

I've also used it to store TODOs and plans. For example I might want to explore some idea and defer it for later, or some weekend have it execute on some tech debt I've put off. One last use case is asking "what did I work on in the last 2-3 weeks, is it healthy, and what additional quality checks can/should I do; is there any follow-up work?"

I find that preserving logs that contain errors will confuse future sessions even if the errors were corrected at the time. Do you have that problem?

Essentially preserving logs extends the context window with all related problems.

I haven’t actually noticed that, but I’m not sure why. Maybe because I specifically describe it to the agent as a work log rather than documentation? I’m not sure

it does not result in great results left unattended, it’ll start creating slop or hardcoding solutions

but overtime if you adjust your verification rubric, it’s not too bad, gets pretty good, if you do make it do TDD, it gets kinda crazy and you’ll have 2000-3000 tests after awhile, or on my common case, 6000-7000 lines of code in single files (i usually have a cron to audit files for decomposition and create tickets)

i wouldn’t use it at my job yet, but it’s been fun to use for personal projects - it’s like modded minecraft automation or factorio

Static analysis can help here! Add CI checks for duplicated code or file length.

For test growth, maybe use a coverage tracker and remove redundant tests?

For me this is ultimate test of self driving. Not all these stages 1-5.

I work in tech. I would be happy to work on gta 6 for 30% of my current income.

In addition to low salary, and crunchtime, the other big downside in the gaming industry is frequently layoffs, and studioes going bust.

You can't ride on a single game for long, and if the next one goes badly half the company will get fired. Not true of the bigger studios, but of course not everybody works in those.

I have friends who work in gaming, and it's a regular thing for studios to form with a great game, go bust a year or three later, and then a new studio get formed with largely similar staff.

Developers move between the same companies around and around again. The lack of stability is a real problem, especially with increasing use of "AI".

Shit can hit the fan with bigger studios when Microsoft or Sony acquire them.

Seconday question, for how long do you think you would be happy with that arrangement?

I just consider this temp phase because models are dumb and harnesses are not yet there.

When I need code review I should just say “review it”. Model should figure out what plugins, skills, etc. to use.

Why does it need plugins/skills for a code review? Claude will just "review it" if you ask it to, and if you have particular preferences, they can go in CLAUDE.md

Skills are effectively the same thing as asking it, just with more depth. So the skill is just a framework for a very precisely asked question. It often includes how you want Claude to respond, etc.

I’m not aware of anything fundamentally unique about skills or commands, they’re just more tokens to shape the llm

Totally. You can do that now, and Claude will know to use /code-review.

I got flashbacks from preparing immigration papers…

In final jewelry no. This is why brands like Tiffany are in panic and pivoting to mechanical-watch-like branding, where only inflated price matters.

I did consider but there are 2 issues. 1. Efficiency. Not all roof parts can be exposed to sun. You overpay 2. You need to time it with roof change

Home insurance also (ie replacement cost after damaging weather event).

I can't help but think that this essentially ruled it out in much of the country -- i get the impression Tesla doesn't tend to consider Midwest markets in their initial engineering

Some apps close window. Some apps close tabs. Some apps can close tab or window. Some apps require double press (chrome)

That’s chrome being a dick - it chrome has an option to undo that (and it’s cmd-q they dickified, not cmd-w).

Oh, you are right. Wrong key

Or you just use iPhone satellite messaging without relying on extra devices that may not even work in mountains

This won't reliably get messages between two users in the mountains.

Neither will Meshtastic!

You can use both. In the mountains I would appreciate redundancy.

All distribution channels that existed before steam are still available. Multiple competitors to steam are available.