danschuller
Joined 12 years ago
Karma
521
Submissions
130
Member since
Jul 23
Joined 12 years ago
- Like normal software engineering - building small parts in isolation, verifying they work and then bringing them together to make the whole.
- Asking Claude to do things using sub-agents to keep the parent context clean. i.e. reviewing plans, research, code reviews
- If there's ever something you can have verification on - a test suite, a screenshot with pixel reading, a certain output to match. Then with `/goal` it tends to work very well with little guidance (in my experience)
- If it keeps getting things wrong, then I make it write a skill. i.e. for some reason it always had errors running playwright but would get there in the end, and it would always have trouble with auth on my NAS but with the skill it can follow the path that's worked for it in the past and not burn tokensThat doesn't sound like a scalable solution. These apps are so pervasive and their use adopted at such a young age (with a large degree of social pressure) it seems like legislation is the only way to curb these dark patterns.
Like other commentators have said these are extremely well resourced companies looking for ways to exploit human psychology at scale. It's in a walled garden, compiled app so it's you have very limited ability to modify what you're shown. End-users of apps need to be given more power over what they can be shown and if that kills companies then to me that's an acceptable tradeoff.
Current side-project: http://www.howtomakeanrpg.com/