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

261–270 of 287 posts

Re: Switch to Claude without starting over

#261

Post by bsder »

TacticalCoder wrote: post #143
bsder wrote: post #56

Earlier quoted context omitted.

> I swear HN is just a bunch of fanboys full of NPC behavior. Why are you assuming these are real people and not NPCs? The amount of money flowing around AI is staggering . To believe that the AI companies aren't flooding all the social media zones with propaganda is disingenuous.

> To believe that the AI companies aren't flooding all the social media zones with propaganda is disingenuous. You don't use "believe" with "disingenuous": it literally makes zero sense. If people honestly believe that, they may be naive. Or they can be "disingenuous" if they're not being sincere. But if you just say what you believe, you're sincere (and maybe naive), and hence cannot possibly be disingenuous.

Hmmm. Good point. I probably knee jerk apply "disingenuous" to everybody AI-adjacent, but I should rethink that given the connotation of "false candor".

"Naive" is certainly a better choice.

Re: Switch to Claude without starting over

#262

Post by toss1 »

thunky wrote: post #260
toss1 wrote: post #256

Earlier quoted context omitted.

Exactly zero of those account for an individual's or company's ability tolive by their own moral code And this AI software is not a mere static object like a hammer that can be handed off to a customer and what it is used for is their business, to build a house or bash a living skull. This is a system that must be constantly maintained by it's builders. Moreover, even if we use your standard, the law, it has already…

> even if we use your standard, the law, it has already been decided in Anthropic's favor. I support Anthropic here. They had a deal with the Govt and the Govt bullied them. That should not be allowed, and Anthropic is suing which makes sense to me. Anthropic should be allowed to set any terms of use for the product that they want, and gain or lose business based on those terms. That's fine. I'm saying that the failu…

Ah, good, we generally agree

For sure, Anthropic should NOT have been forced to decide the ethics of deploying their tech

Nevertheless, they should always be considering the ethics of their own creations and actions, and it seems they are — as soon as they got bullied by a failing regime, they had the right answer: 'no, that is not ethical and we won't allow it with our products'.

The problem is that the law only very roughly captures what is right and just, so there are many things that are legal that are unethical, at the same time there are many things that are ethical but illegal. So, we can't entirely outsource our personal or corporate ethics to the law.

Re: Switch to Claude without starting over

#263

Post by skeledrew »

ben_w wrote: post #193
skeledrew wrote: post #176

Earlier quoted context omitted.

> 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.

For the swift apps, at least half of the errors are of a type where I wouldn't expect to have needed to tell someone to not do it like that, and only a student could reasonably be expected to not know better. For the python physics sim, step 1 was to generate the plan, the prompt included "I want actual plasma physics, including high-density, high-field regimes, externally applied fields, etc., so consider which FOSS…

Definitely give Claude a go. I've been nothing but impressed by the performance thus far. My only gripe is the usage limit that I keep hitting.

Re: Switch to Claude without starting over

#264

Post by peteforde »

whaleidk wrote: post #183
peteforde wrote: post #89

Earlier quoted context omitted.

I see this over and over again. I don't dispute your experience. My experience with ESP32 development has been unreasonably positive. My codebase is sitting around 600k LoC and is the product of several hundred Opus 4.x Plan -> Agent -> Debug loops. I review everything that goes through, but I'm reviewing the business logic and domain gotchas, not dumb crap like what you and so many others describe. What is so strang…

600k lines of code for anything on the ESP32 sounds like the absolute polar opposite of “good”

Tell us you've never built anything significant without telling us?

Re: Switch to Claude without starting over

#265

Post by peteforde »

the__alchemist wrote: post #221
surajrmal wrote: post #182

Earlier quoted context omitted.

I don't think it's that large. Keep in mind embedded projects take few if any dependencies. The standard library in most languages is far bigger than 600k loc.

I'm curious: What does this device do?

It's wild to come back to this after a day away and have the takeaway from my attempt to answer the question with punditry about the size of my codebase from people who don't have any idea what my device does.

Answering this question directly puts me in an awkward spot because I realized last fall that there was absolutely no way that I could talk about what I'm working on in a way that can be associated with my product because there's so much anti-AI activism right now. That sucks, because I'd like to be "loud and proud" but I have a family to feed. I strongly suspect that versions of my story are playing out for hundreds of entrepreneurs right now.

Here's what I can describe: it's an ESP32-P4 based consumer device with about 45 ESP-IDF components that all communicate over an event bus. There's a substantially modified LVGL front-end with a 3D rendering engine and SVG-like 2D animation in front of a driver for a customized variation of the ST7789. There is substantial custom code for both USB host and client functions across various modes of operation. There's custom drivers for several sensors and haptic feedback. There's a very elaborate menu UI system which is also backed by a BBS style terminal configuration system for power users. There's an assignable action system with about 40 actions that all have their own state machines and a lot of mutex locking. There's a very involved and feature-dense trigger scheduling system. There's a very flexible data stream routing matrix. There's a full suite of command line scripts for most functions. There's a self-hosted web app for configuration that also implements a screen share functionality via an HTML canvas object so that I can record videos of what's happening on the device with OBS without having to point a DSLR at it from a gantry.

Honestly, I could go on and on, but all of the people who think that 600kloc is a lot [sight unseen] are following YouTube tutorials and can eat me.

I responded to you because you asked politely. I hope it was an interesting reply.

Re: Switch to Claude without starting over

#266

Post by AlecSchueler »

ivan_gammel wrote: post #102
AlecSchueler wrote: post #58

Earlier quoted context omitted.

> Its the only model that gets production ready output on the first detailled prompt. Yesterday I used my tokens til noon, so I tried some output from Gemini & Co. I presented a working piece of code which is already in production: One does often hear that where LLMs shine is with greenfield code generation but they all start to struggle working with pre-existing code. It could be that this wasn't a like for like com…

Greenfield implementation is not flawless as well.

"better at" != "flawless"

Re: Switch to Claude without starting over

#267

Post by ben_w »

skeledrew wrote: post #263
ben_w wrote: post #193

Earlier quoted context omitted.

For the swift apps, at least half of the errors are of a type where I wouldn't expect to have needed to tell someone to not do it like that, and only a student could reasonably be expected to not know better. For the python physics sim, step 1 was to generate the plan, the prompt included "I want actual plasma physics, including high-density, high-field regimes, externally applied fields, etc., so consider which FOSS…

Definitely give Claude a go. I've been nothing but impressed by the performance thus far. My only gripe is the usage limit that I keep hitting.

Already have done, hence earlier comment: https://news.ycombinator.com/item?id=47204959

Claude made far fewer mistakes in general, never gave me non-compiling code.

Re: Switch to Claude without starting over

#268

Post by euroderf »

The HN headline sounded like it would help me spring Claude onto an existing project. Which would let me try it on my pre-existing code without having Claude "accidentally" trash the works. I fret because I keep reading that people tell the A.I. not to do things to repos and then the A.I. does them anyways.

Pointers, anyone ?

Re: Switch to Claude without starting over

#269

Post by ymolodtsov »

deaux wrote: post #17
jjmarr wrote: post #7

Earlier quoted context omitted.

Most normal people want the LLM to remember their interests and favourite things, so they don't have to manually re-explain when asking for advice. They also don't know what "context" is or that the LLM has a limited number of tokens it can understand at any given time. They just believe it knows everything at once.

Do you have example prompts where this would be usual? Why would you want an LLM to know your favorite type of cheese? Now that I say that, I guess if you use it for recipes then it's useful if it remembers things like dietary restrictions. And even then a project seems like the better option. I can't think of much else though so I'm still curious what you or others use it for.

I was redoing our agency's website and thinking about new sections. Claude already knows who I am and what do we do, so it was able to offer extremely relevant suggestions based on this without any further prompting.

In my personal experience the memory in Claude works much better than in ChatGPT where it indeed feels forced and leads to "remember the user loves cheese" moments.

Post reply on HN