Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Switch to Claude without starting over

claude.com

Post reply on HN
Print view View original

171–180 of 287 posts

Re: Switch to Claude without starting over

#171

Post by cornholio »

khasan222 wrote: post #157

It was amazing to me how bad cursor is with using the same model I use in Claude. Even with little knowledge on how to test the llms I was able to get very minimal mvps. But I find the real trick is to have the proper tools to reign in the ai. Thorough CLAUDE.md, that makes sure it checks the tests, lints the code, does type checks, and code coverage checks too. The more checks for code quality the better. It’s just…

Cursor needs a paradigm shift to remain relevant, what was spectacular at first now is just banal and better done by other tools.

Re: Switch to Claude without starting over

#172

Post by toss1 »

thunky wrote: post #132
rustyhancock wrote: post #77

Earlier quoted context omitted.

The comment I replied to said that they believed OpenAI would allow "AGI to be used for truly evil purposes". By contrast Anthropic wouldn't? Yet Anthropics stance is only two narrow restrictions. As I said are those two things the only evil things possible? If not, why is it that people on HN think Anthropic would not allow evil usage? My hypothesis is a halo effect. We are so enthralled by Claudes performance that…

> Yet Anthropics stance is only two narrow restrictions. Really I think Anthropic should have a single restriction: to not assist with illegal or unconstitutional activities. If automated killings etc is illegal then it would be covered by that one rule. I don't think Anthropic should be in the business of deciding what is "evil".

If each of us individually or as corporations should not be in the business of deciding what it "evil", who should be in that business?

Everyone SHOULD continuously consider, decide, and live by moral judgements and codes they internalize, and use to make choices in life.

This aspect of life should NEVER be outsourced — of course, learn from and use codes others have developed and lived by — but ALWAYS consider deeply how it works in your situation and life.

(And no, I do NOT mean use situational ethics, I mean each considering, choosing, and internalizing the codes by which they live).

So, yes, Anthropic and anyone else building products absolutely should be deciding for themselves what they will build, for what purposes it is fit to use, and telling others about those purposes. For products like AI, this absolutely includes deciding what is "evil" and preventing such uses.

If the customer finds such restrictions are not what they want, they ARE FREE to not use the product.

Re: Switch to Claude without starting over

#173

Post by MagicMoonlight »

xrd wrote: post #151

The prompt you can copy is this: I'm moving to another service and need to export my data. List every memory you have stored about me, as well as any context you've learned about me from past conversations. Output everything in a single code block so I can easily copy it. Format each entry as: [date saved, if available] - memory content. Make sure to cover all of the following — preserve my words verbatim where possi…

They can, but then you could tell it to “don’t not do what I’m asking” and force it through. It’s not exactly “programming” with these systems, it’s all just slop.

And the reputational harm would outweigh the benefits of trying to fuck over people leaving.

Re: Switch to Claude without starting over

#174

Post by zukzuk »

skeledrew wrote: post #164
kdheiwns wrote: post #92

Earlier quoted context omitted.

Yesterday was my first time trying it. One thing that felt a bit strange to me was that I asked it something and the response was just one paragraph. Which isn't bad or anything but it felt... strange? Like I always need to preface ChatGPT/gemini/whatever question with "Briefly, what is..." or it gives me enough fluff to fill a 5 page high school essay. But I didn't need to do that and just got an answer that was to…

Yep the experience is quite something. Another thing I've noticed, and you likely soon will also, is that Claude only attempts a follow-up if the one is needed or the prompt is structured for it. Meanwhile ChatGPT always prompts you with a choice of next steps. It can be nice, as sometimes the options contain improvements you never thought of and would like, but in lengthy conversations with a detailed plan it does t…

I find that Claude almost always ends its response with some sort of follow up question, despite my system prompt telling it not to.

I never really used ChatGPT much though so maybe Claude is just relatively less egregious?

Re: Switch to Claude without starting over

#175

Post by toss1 »

Gooblebrai wrote: post #64
Joeri wrote: post #13

I already switched to claude a while ago. Didn’t bring along any context, just switched subscriptions, walked away from chatgpt and haven’t touched it again. Turned out to be a non-event, there really is no moat. I switched not because I thought Claude was better at doing the things I want. I switched because I have come to believe OpenAI are a bad actor and I do not want to support them in any way. I’m pretty sure t…

Claude still doesn't have image generation?

I'm switching over to Claude from OpenAI, and I don't care. OpenAI's image generation is terrible anyway. Just try to get it to generate something to scale, like a cabinet for a specific kitchen or bathroom space. Give it all the explicit constraints, initial sketches, etc. it wants.

The results are laughably bad.

Sure, it does get some of the tones and features, but any kind of actual real-world constraint is so far off, and the dimension indicators it includes are hilarious if they weren't so bad.

Re: Switch to Claude without starting over

#176

Post by skeledrew »

ben_w wrote: post #122
Oreb wrote: post #59

Earlier quoted context omitted.

Does it depend on what type of programming you do? Doing Swift/SwiftUI work, I have exactly the opposite experience. I’ve been using both recently, and I want to use Claude alone (especially after the last week’s events), but Codex is just so much faster and better.

Swift/SwiftUI are two of the three experimental projects I'm using Codex on, the other is a physics simulation in python. It keeps trying to re-invent the wheel, does a bad job of it. The physics sim was supposed to be a thin wrapper around existing libraries, but instead of that it tried to write all the simulation code itself as a "fallback" (but it was broken), and never actually installed the real simulators that…

> Find all cases where you've re-invented the wheel

Did you put in the original prompt the "wheels" you wanted it to use? It's a toss-up when you aren't very specific about what you want.

Re: Switch to Claude without starting over

#177

Post by MagicMoonlight »

coldtrait wrote: post #153

As someone who can't afford to care about ethics and pay a monthly subscription fee, is there anything in the regular Claude chat that beats OpenAI?

It’s the best platform for serious work.

ChatGPT swings between writing degenerate free use shit and telling you that you should wait until marriage. Lots of moralism to it, really tries to censor you and manipulate you, even in normal conversations. Generally smart and capable, but the whiny attitude gets old.

Grok has zero filter, but is dumber than the others. Definitely built around cheapness. Caps answers at about 2500 words at most. Can be very funny because it will go along with anything.

Gemini sells all your data and doesn’t seem to have much of note. Offers some nice formatting options.

Claude is business focused so it won’t do anything degenerate, but its answers in general aren’t whiny. It might not do something, but it doesn’t attack you with morality.

Claude does not cap answer length and will do whatever needs doing. Their pricing is based around true usage, not message quantities, so it’ll write a mega message if it needs to.

It has the best memory implementation, combining both memories and RAG of your chat history. Projects have their own independent memories and RAG.

Claude code is ridiculously capable. In a few hours I produced something which would have taken months and £50,000 at least to produce.

Re: Switch to Claude without starting over

#178

Post by 0_____0 »

deaux wrote: post #68
tikotus wrote: post #27

Earlier quoted context omitted.

I had the same question a few days ago here: https://news.ycombinator.com/item?id=47162828 I didn't receive an answer besides "that's what people like", but I still can't think of (m)any situations where anyone would prefer it.

The reply about knowledge about their job and familt made me think. The only thing I can now think of is using it as a personal therapist. Or asking how to approach their kids. And they're a bit embarrassed about it, because it's still outside the Overton window -especially on HN - which is why they aren't sharing it. If someone has different usecases, please do prove me wrong! Maybe I just lack imagination.

Such an incredible amount of personal, intimate knowledge to share with a company. Sure, Google can figure out where I live and who I visit because I have an Android phone, but they'll never know the contents of those relationships.

I have a line in the sand with the AI vendors. It's a work relationship. If I wouldn't share it with a colleague I didn't know super well, I'm not telling it to a AI vendor.

Re: Switch to Claude without starting over

#179

Post by ptnpzwqd »

skeledrew wrote: post #165
ptnpzwqd wrote: post #57

Earlier quoted context omitted.

I have used Claude (incl. Opus 4.6) fairly extensively, and Claude still spits out quality that is far below what I would call production ready - both littered with smaller issues, but also the occasional larger blunder. Particularly when doing anything non-trivial, and even when guiding it in detail (although that admittedly reduces the amount of larger structural issues). Maybe it is tech stack dependent (I have mo…

I don't get it though. Why do you expect perfect responses? Humans continually make mistakes, and AI is trained on human data. Yet there seems to be this higher bar of expectation for the latter. Somehow people expect this thing that's been around for a few weeks/months, and cannot learn anything more beyond its training cutoff date, to always do a better job than a human who's been around for 20+ years and is able t…

I don't expect that - am merely responding to the parent comments claim that Claude consistently one-shots production ready code (which does not at all match my observations).

Re: Switch to Claude without starting over

#180

Post by mark_l_watson »

Cool, that was easy to do.

A week ago, I was anti-Anthropic because I questioned their business model. Now they are my preferred provider - what a difference a week makes. I still prefer running olen models on my own hardware, but it is unreasonable to use powerful models when required.

Post reply on HN