boxedemp

Big "Kill them with kindness" energy.

I have my own harness I wrap Claude CLI in, I wonder if I'm breaking the rules...

Neither was either of mine, but I don't advertise them and specifically don't post them on social media

I think that's a cool project, though I found the results to be less relevant than Google.

There's supposed to be for many (not all) use cases.

To be clear I never said or implied it wasn't helping c++ devs. I said I find it helps HTLM/JS development more.

And I don't even think it'll stay that way, just that it's what I've seen so far.

It's anecdotal of me, I apologize for that.

Interesting perspective.

I guess I'm more interested in understanding what it can and can't do.

I don't find it tiresome at all. What I was getting at was, even with constant justifications you need to remain vigilant.

I've been alive for several decades and almost nothing I've gotten was exactly as advertised.

I'm not saying that's good, but it's consistent with reality.

I get it, but it makes me sad.

At least I already have it in my library so, looks like I still get updates.

They paid to interact with a computer, and they did. On the Internet nobody knows I'm a dog, and that's ok.

How do they know? Not everybody includes to coauthored by Claude. I certainly don't.

It has a lot. I find by challenging it often, getting it to explain it's assumptions, it's usually guessing.

This can be overcome by continuously asking it to justify everything, but even then...

Phone is probably the best tool for most minor online banking actions.

Not all.

Fantastic! I had been using dockers but this might be better!

So.. you should build the new slack?

Call it Lull

Maybe we should drop one of the L's

We'll fix it if it become cost effective. It might, but probably won't because if the scale.

I'm with you. The project I'm working on is moving at phenomenal velocity. I'm basically spending my time writing specs and performing code reviews. As long as my code review comments and design docs are clear I get a secure, scalable, and resilient system.

Tests were always important, but now they are the gatekeepers to velocity.

I'm sure they're collecting all kinds of insights from the prompts.

I think it really depends what you're working on. I do some consulting and found it's not helping the C++ devs as much it's helping the html/js devs.

Amazon usually has 3 AVs per region, looks like there are surviving AVs but the system didn't switch over gracefully.

I bet that was an interesting sev2 ticket!

I find it very much matters. I find Gemini better for pretty frontends, Claude opus for planning. Gemini and opus for code reviews. Codex is great when I want the LLM do follow instructions more strictly- good if you already have a detailed design.

Definitely depends on your use.

It's already happened in the Korean DMZ

Killing people has been legal forever. But you have to do it at scale for it to be legal.

The part about money

As time goes on RMS is only proven more and more correct

You don't need modern ai for that, it's been done decades ago.

Modern tools lend themselves more to information warfare and deobfuscation.

The threat seems straightforward to me; information warfare.

Amazing work! I look forward to an API if/when you release it!