tqwhite

using spreadsheet to prototype thing == good idea

I installed it as cd. I do not think I ever, even a single time, used it differently from normal cd. It turns out that my system is organized so that I know where everything is.

On the rare occasion something is lost, it's a file, not a directory. Then I Spotlight (Mac super find) because it also searches content

Could it really be worth it to try to build new shell commands into muscle memory? How long would it take before

err "some message"

becomes normal?

For me, it would have to offer sexual favors or something to be worth it. I don't see anything that good otherwise.

The amount of bandwidth they use is trivial. That's not an issue.

I don't have any idea if the poisoning idea is real or not. I express contempt for those that think it's a good idea. It's not just my support for AI learning from the public internet, there are also people who will see it. It's unethical.

You put it on the public internet, the public has the right to see it, take whatever lessons it can and do what it wants. It's the intrinsic nature of the internet.

It has never been ok to say, "[this kind of person] is not allowed to look at my page nor, "you can only look at my page with [this web browser or other tool]".

If you have posted public web pages then the fact of your being able to be seen by people using the public network infrastructure is your payment.

If you put stuff outside, in public, then it is correct for people to observe and learn from it. You should be happy that your web presence is enriching our culture. If not, you're selfish and I think you're bad.

If you don't want it to contribute to the public use, make a login page. I see no reason for you to get the advantage of a public access without contributing to the community.

I continue to have contempt for the "I'm not contributing to the enrichment of our newest and most powerful technology" gang. I do not accept the assertion that my AI should have any less access to the internet that we all pay for than I do.

If guys like this have their way, AI will remain stupid and limited and we will all be worse off for it.

What a load of crap. I don't believe it for one second. Also, AI has only been an important influence for about twenty minutes.

Here's what I think: AI causes you to forget how to program but causes you to learn how to plan.

Also, AI enhances who you are. Dummies get dummer. Smarties get smarter.

But that's not proven. It's anecdote. And I don't believe anyone knows what is really happening and those that claim to are counterproductive.

You can. You can jailbreak your iPhone. I assume you can do so with Android. Problem solved.

Oh, you want to jailbreak it and use it as an authenticator? No. That doesn't seem like a reasonable requirement.

I have exactly one to choose from. Two thirds of americans households have exactly two, exactly the same number as the count of googles and apples.

When you let Claude run free over changes big enough to have this thing be meaningful, are you really getting good enough code?

When I just set Claude loose for long periods, I get incomprehensible, brittle code.

I don't do maintenance so maybe that's the difference but I have not had good results from big, unsupervised changes.

I love DEET. It is absolutely the perfect way to avoid mosquitos and ticks.

At home though, I use Thermacell. It's the only thing I have ever used that makes a measurable difference. Of course, you need to have one ever four or five feet unless the air is perfectly still but that's a small price.

Every time I have read science guys about things that you can do to kill mosquitos there is an analogy to putting a drain in the ocean. You can kill mosquitos at a fantastic rate but, unless you are also killing them in all your neighbor's yards for a mile around, they are just going to keep coming as fast as they die.

I use API but think about getting the $100/mo plan and using API for overflow if it occurs.

But I have slow months and think that might not actually be the winner. Basically I'm going to wait and see before I sign up for auto-pay.

This is my strategy as well. I definitely have surges of usage.

Except for one catastrophic binge where I accidentally left Opus on for a whole binge (KILL ME!!!), I use around $150/month. I like having the spigot off when I am not working.

Would the $100/month plan plus API for overflow come out ahead? Certainly on some months. Over the year, I don't know. I'll let you know.

There was some capital expenditure that had to be paid for.

In the US, ATT was just barely deregulated by then so the prices were not just 'out of thin air'.

With one months exception, I've never gotten past $150 with API. I plan to do the $100 plan and use the API for overflow. I think I will come out ahead.

Don't you also have an API subscription to provide overflow capacity?

I don't blame them for worrying about it. The policy should not be to forbid it but make sure you don't leave artifacts because I guarantee, people are going to use a bot to write their code. Hell, in six months, I doubt you will be able to get a code editor that doesn't use AI for code completion at least.

Also, AI coded programs will be copyrightable just like the old days. You think the big corps are going to both not use bot coding and give up ownership of their code? Fat chance.

Remember the Micky Mouse copyright extension? If the courts aren't sensible, we will have one of those the next day.

The old days ended very abruptly this time.

This is the worst thread I have ever seen on Hacker News. Fatuous, self-important, superficial, judgmental. Do better people.

Definitely a new skill to learn. Everyone I know that is having problems is just telling it what to do, not coaching it. It is not an automaton... instructions in code out. Treat it like a team member that will do the work if you teach it right and you will have much more success.

But is definitely a learning process for you.

I find that writing a thorough design spec is really worth it. Also, asking for its reaction. "What's missing?" "Should I do X or Y" does good things for its thought process, like engaging a younger programmer in the process.

Definitely, I ask for a plan and then, even if it's obvious, I ask questions and discuss it. I also point it as samples of code that I like with instructions for what is good about it.

Once we have settled on a plan, I ask it to break it into phases that can be tested (I am not one for a unit testing) to lock in progress. Claude LOVES that. It organizes a new plan and, at the end of each phase tells me how to test (curl, command line, whatever is appropriate) and what I should see that represents success.

The most important thing I have figured out is that Claude is a collaborator, not a minion. I agree with visarga, it's much more like surfing that walking. Also, Trust... but Verify.

This is a great time to be a programmer.

I've been using Claude Code, ie, a terminal interface to Sonnet 3.7 since the day it came out in mid March. I have done substantial CLI apps, full stack web systems and a ton of utility crap. I am much more ambitious because of it, much as I was in the past when I was running a programming team.

I'm sure it is much the same as this under the hood though Anthropic has added many insanely useful features.

Nothing is perfect. Producing good code requires about the same effort as it did when I was running said team. It is possible to get complicated things working and find oneself in a mess where adding the next feature is really problematic. As I have learned to drive it, I have to do much less remediation and refactoring. That will never go away.

I cannot imagine what happened to poor kgeist. I have had Claude make choices I wouldn't and do some stupid stuff, never enough that I would even think about giving up on it. Almost always, it does a decent job and, for a most stuff, the amount of work it takes off of my brain is IMMENSE.

And, for good measure, it does a wonderful job of refactoring. Periodically, I have a session where I look at the code, decide how it could be better and instruct Claude. Huge amounts of complexity, done. "Change this data structure", done. It's amazingly cool.

And, just for fun, I opened it in a non-code archive directory. It was a junk drawer that I've been filling for thirty years. "What's in this directory?" "Read the old resumes and write a new one." "What are my children's names?" Also amazing.

And this is still early days. I am so happy.

It doesn't seem expensive to me at all. It does a huge amount.

This looks like a very cool and very fun tool. Perfecting its use will be a much better way to avoid real work than scrolling instagram.

I think the whole internet is a free lunch problem as far as that goes. I pay for web hosting because I consider the cost to be worth it to send my fabulous opinions into the ether.

The premise of this thread is that somehow the LLM builders are reading too much. I bet it's less than google.

I continue to believe, if you don't want everyone in the world to see and use your stuff, don't put it on the internet.

I doubt that AI will ever figure out 'what to do' since it doesn't have a body and can't get out in the world.

But, if it does, I will go the way of all those buggy whip makers and find something else to do. (And it will probably be doing something with AI.)

"so it doesn't matter what you think"

A perfectly fine, if incorrect reply, but then you have to be a dick. Why?

That's untrue. See my comment elsewhere around here. It doesn't rely on the commercial aspect, though if it's not commercial the bar for fair use is set lower.

The argument in Warhol relies on the fact that the derivative work, ie, Warhol's painting, is substantially similar in function to the original photograph. If Warhol had used the picture as stuffing for a soft sculpture, it would not infringe.

LLM is closer to the latter than the former.