CLAUDE.md is read on session startup.

If you're continually finding that it's being forgotten, maybe you're not starting fresh sessions often enough.

hansmayer 8 hours ago | parent | next [-]

I should not have to fight tooling, especially the supposedly "intelligent" one. What's the point of it, if we have to always adapt to the tool, instead of the other way around?

▲

kfajdsl 8 hours ago | parent [-]

It's a tool. The first time you used a shell you had to learn it. The first time you used a text editor you had to learn it.

You can learn how to use it, or you can put it down if you think it doesn't bring you any benefit.

▲

PunchyHamster 5 hours ago | parent | next [-]

even shell remembers my commands...

▲

hansmayer 8 hours ago | parent | prev [-]

I am sorry but what do I have to learn? That the tool does not work as advertised? That sometimes it will work as advertised, sometimes not? That it will sometimes expose critical secrets as plain text and some other time suggest to solve a problem in a function by removing the function code completely? What are you even talking about, comparing to shell and text editors? These are still bloody deterministic tools. You learn how they work and the usage does not change unpredictably every day! How can you learn something that does not have predictable outputs?

▲

simonw 6 hours ago | parent [-]

Yes, you have to learn those things. LLMs are hard to use.

So are animals, but we've used dogs and falcons and truffle hunting pigs as tools for thousands of years.

Non-deterministic tools are still tools, they just take a bunch more work to figure out.

▲

xn 6 hours ago | parent | next [-]

It's like having Michael Jordan with dementia on your team. You start out mesmerized by how many points he can score, and then you get incredibly frustrated that he forgets he has to dribble and shoot into the correct hoop.

▲

exasperaited 5 hours ago | parent | prev [-]

> So are animals, but we've used dogs and falcons and truffle hunting pigs as tools for thousands of years.

Dogs learn their jobs way faster, more consistently and more expressively than any AI tool.

Trivially, dogs understand "good dog" and "bad dog" for example.

Reinforcement learning with AI tooling clearly seems not to work.

	▲	simonw 3 hours ago \| parent [-]
		> Dogs learn their jobs way faster, more consistently and more expressively than any AI tool. That doesn't match my experience with dogs or LLMs at all.

▲

exasperaited 5 hours ago | parent | prev [-]

I understand you're trying to be helpful but the number of "you're holding it wrong" things I read about this tool — any AI tool — just makes me wonder who vibe coders are really doing all this unpaid work for.