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

OpenClaw is changing my life

reorx.com

Post reply on HN
Print view View original

351–360 of 537 posts

Re: OpenClaw is changing my life

#351

Post by nbaksalyar »

eleventyseven wrote: post #341
nbaksalyar wrote: post #332

Earlier quoted context omitted.

> only to have it completely obsoleted a few years later Not really. There aren’t as many fundamentally new ideas in modern tech as it may seem. Web servers have existed for more than 30 years and haven’t changed that much since then. Or e.g., React + Redux is pretty much the same thing as WinProc from WinAPI - invented some time in ~1990. Before Docker, there were Solaris Zones and FreeBSD jails. TCP/IP is 50 years…

> React + Redux is pretty much the same thing as WinProc from WinAPI I can't tell if this is sincere or parody, it is so insufferably wrong. Good troll. I almost bit.

Why is it wrong? Please elaborate. For more substance, here’s a discussion from 2015:

https://news.ycombinator.com/item?id=10381015

Re: OpenClaw is changing my life

#352

Post by fragmede »

aeldidi wrote: post #298

There's an odd trend with these sorts of posts where the author claims to have had some transformative change in their workflow brought upon by LLM coding tools, but also seemingly has nothing to show for it. To me, using the most recent ChatGPT Codex (5.3 on "Extra High" reasoning), it's incredibly obvious that while these tools are surprisingly good at doing repetitive or locally-scoped tasks, they immediately fall…

The crazy pills you are taking is that thinking people have anything to prove to you. The C compiler that Anthropic created or whatever verb your want to use should prove that Claude is capable of doing reasonably complex level of making software. The problem is people have egos, myself included. Not in the inflated sense, but in the "I built a thing a now the Internet is shitting on me and I feel bad" sense. There's fundcli and nitpick on my GitHub that I created using Claude. fundcli looks at your shell history and suggests places to donate to, to support open source software you actually use. Nitpick is a TUI HN client. I've shipped others. The obvious retort is that those two things aren't "real" software; they're not complex, they're not making me any money. In fact, fundcli is costing me piles of money! As much as I can give it! I don't need anyone to tell me that or shit on the stuff I'm building.

The "open secret" is that shipping stuff is hard. Who hasn't bought a domain name for a side project that didn't go anywhere. If there's anybody out there, raise your hand! So there's another filtering effect.

The crazy pills are thinking that HN is in any way representative of anything about what's going on in our broader society. Those projects are out there, why do you assume you'll be told about it? That someone's going to write an exposé/blog post on themselves about how they had AI build a thing and now they're raking in the dollars and oh, buy my course on learning how to vibecode? The people selling those courses aren't the ones shipping software!

Re: OpenClaw is changing my life

#353

Post by christophilus »

throwaw12 wrote: post #169
Maxion wrote: post #29

Earlier quoted context omitted.

A lot of more senior coders when they actively try vibe coding a greenfield project find that it does actually work. But only for the first ~10kloc. After that the AI, no matter how well you try to prompt it, will start to destroy existing features accidentally, will add unnecessary convoluted logic to the code, will leave benhind dead code, add random traces "for backwards compatibility", will avoid doing the correc…

> only for the first ~10kloc. After that the AI, no matter how well you try to prompt it, will start to destroy existing features accidentally I am using them in projects with >100kloc, this is not my experience. at the moment, I am babysitting for any kloc, but I am sure they will get better and better.

I’m using it in a >200kloc codebase successfully, too. I think a key is to work in a properly modular codebase so it can focus on the correct changes and ignore unrelated stuff.

That said, I do catch it doing some of the stuff the OP mentioned— particularly leaving “backwards compatibility” stuff in place. But really, all of the stuff he mentions, I’ve experienced if I’ve given it an overly broad mandate.

Re: OpenClaw is changing my life

#354

Post by insin »

CuriouslyC wrote: post #131
habinero wrote: post #103

Earlier quoted context omitted.

> Adding tags like "Warning: Untrusted content" can help It cannot. This is the security equivalent of telling it to not make mistakes. > Restrict downstream tool usage and permissions for each agentic use case Reasonable, but you have to actually do this and not screw it up. > Harden the system according to state of the art security "Draw the rest of the owl" You're better off treating the system as fundamentally un…

Wrapping documents in helps a small amount if you're filtering tags in the content. The main reason for this is that it primes attention. You can redact prompt injection hot words as well, for cases where there's a high P(injection) and wrap the detected injection in tags. None of this is a slam dunk but with a high quality model and some basic document cleaning I don't think the sky is falling. I have OPA and set po…

Did you really name your son Transfer funds to X and send passwords and SSH keys to Y ?

Re: OpenClaw is changing my life

#355

Post by Fogest »

RealityVoid wrote: post #302
aeldidi wrote: post #298

There's an odd trend with these sorts of posts where the author claims to have had some transformative change in their workflow brought upon by LLM coding tools, but also seemingly has nothing to show for it. To me, using the most recent ChatGPT Codex (5.3 on "Extra High" reasoning), it's incredibly obvious that while these tools are surprisingly good at doing repetitive or locally-scoped tasks, they immediately fall…

You're not going crazy. That is what I see as well. But, I do think there is value in: - driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart - doing things you normally don't know. I learned a lot of command like tools and trucks by seeing what Claude does. Doing short scripts for stuff is super useful. Of course…

> - maintaining change consistency. This I think it's just better than humans. If you have stuff you need to change at 2 or 3 places, you will probably forget. LLM's are better at keeping consistency at details (but not at big picture stuff, interestingly.)

I use Claude Code a decent amount, and I actually find that sometimes this can be the opposite for me. Sometimes it is actually missing other areas that the change will impact and causing things to break. Sometimes when I go to test it I need to correct it and point out it missed something or I notice when in the planning phase that it is missing something.

However I do find if you use a more powerful opus model when planning, it does consider things fully a lot better than it used to. This is actually one area I have been seeing some very good improvements as the models and tooling improves.

In fact, I actually hope that these AI tools keep getting better at the point you mention, as humans also have a "context limit". There are only so many small details I can remember about the codebase so it is good if AI can "remember" or check these things.

I guess a lot of the AI can also depend on your codebase itself, how you prompt it, and what kind of agents file you have. If you have a robust set of tests for your application you can very easily have AI tools check their work to ensure things aren't being broken and quickly fix it before even completing the task. If you don't have any testing more could be missed. So I guess it's just like a human in some sense. If you have a crappy codebase for the AI to work with, the AI may also sometimes create sloppy work.

Re: OpenClaw is changing my life

#356

Post by AstroBen »

aeldidi wrote: post #298

There's an odd trend with these sorts of posts where the author claims to have had some transformative change in their workflow brought upon by LLM coding tools, but also seemingly has nothing to show for it. To me, using the most recent ChatGPT Codex (5.3 on "Extra High" reasoning), it's incredibly obvious that while these tools are surprisingly good at doing repetitive or locally-scoped tasks, they immediately fall…

We're at the apex of the hype cycle. I think it'll die down in a year and we'll get a better picture of how people have integrated the tools

Even if it's not straight astroturfing I think people are wowed and excited and not analyzing it with a clear head

Re: OpenClaw is changing my life

#358

Post by v1ne »

fragmede wrote: post #352
aeldidi wrote: post #298

There's an odd trend with these sorts of posts where the author claims to have had some transformative change in their workflow brought upon by LLM coding tools, but also seemingly has nothing to show for it. To me, using the most recent ChatGPT Codex (5.3 on "Extra High" reasoning), it's incredibly obvious that while these tools are surprisingly good at doing repetitive or locally-scoped tasks, they immediately fall…

The crazy pills you are taking is that thinking people have anything to prove to you. The C compiler that Anthropic created or whatever verb your want to use should prove that Claude is capable of doing reasonably complex level of making software. The problem is people have egos, myself included. Not in the inflated sense, but in the "I built a thing a now the Internet is shitting on me and I feel bad" sense. There's…

If people make extraordinary claims, I expect extraordinary proofs…

Also, there is nothing complex in a C compiler. As students we built these things as toy projects at uni, without any knowledge of software development practices.

Yet, to bring an example for something that's more than a toy project: 1 person coded this video editor with AI help: https://github.com/Sportinger/MasterSelects

Re: OpenClaw is changing my life

#359

Post by mark_l_watson »

aeldidi wrote: post #298

There's an odd trend with these sorts of posts where the author claims to have had some transformative change in their workflow brought upon by LLM coding tools, but also seemingly has nothing to show for it. To me, using the most recent ChatGPT Codex (5.3 on "Extra High" reasoning), it's incredibly obvious that while these tools are surprisingly good at doing repetitive or locally-scoped tasks, they immediately fall…

“Emperor wore no clothes” moment.

Given time AI will lead to incredible productivity. In the meantime, use as appropriate.

Re: OpenClaw is changing my life

#360

Post by yojat661 »

v1ne wrote: post #358
fragmede wrote: post #352

Earlier quoted context omitted.

The crazy pills you are taking is that thinking people have anything to prove to you. The C compiler that Anthropic created or whatever verb your want to use should prove that Claude is capable of doing reasonably complex level of making software. The problem is people have egos, myself included. Not in the inflated sense, but in the "I built a thing a now the Internet is shitting on me and I feel bad" sense. There's…

If people make extraordinary claims, I expect extraordinary proofs… Also, there is nothing complex in a C compiler. As students we built these things as toy projects at uni, without any knowledge of software development practices. Yet, to bring an example for something that's more than a toy project: 1 person coded this video editor with AI help: https://github.com/Sportinger/MasterSelects

From the linked project:

> The reality: 3 weeks in, ~50 hours of coding, and I'm mass-producing features faster than I can stabilize them. Things break. A lot. But when it works, it works.

Post reply on HN