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

501–510 of 537 posts

Re: OpenClaw is changing my life

#501

Post by joks »

xXSLAYERXx wrote: post #495
joks wrote: post #493

Earlier quoted context omitted.

Are you saying you were forced to go into management because you felt like you couldn't be an effective engineer without working overtime? I'm confused. That sounds more like your work environment was terrible

You're spot on. And maybe I've only ever worked in terrible eng environments which is an interesting thought for me. I'll have to reflect on this. Sounds like you've had the opposite experience?

My workplace at least values work/life balance and buys into the idea that workers who aren't burnt out are more likely to stick around long-term and do good work (which I've found to be true in my own experience so far.) If we can't get done what we need to get done in a 40h workweek, then that's a failure of higher-level planning (or that we're simply understaffed), not that ICs need to be working overtime.

Re: OpenClaw is changing my life

#502

Post by jdrhyne »

Same experience here. What pushed it over the top for me was adding document processing via the nutrient-openclaw plugin — my agent can now convert, OCR, redact, and sign PDFs without me switching tools. It's a native OpenClaw plugin so you just install and it's available.

https://github.com/PSPDFKit-labs/nutrient-openclaw -

The skill is here as well if you prefer a skill - https://clawhub.ai/jdrhyne/nutrient-openclaw

Re: OpenClaw is changing my life

#503

Post by Dylan16807 »

rafabulsing wrote: post #498
Dylan16807 wrote: post #435

Earlier quoted context omitted.

> Which I think is what people gather from him, but somehow think he's hiding it or pretending is not the case? Which I find strange, given how openly he's talked about it. Well the person you're responding to didn't say anything like that. They're saying he's unqualified. > The systems and habits are the ways he found to essentially trick himself into working. And do they work ? If he's failing or fooling himself th…

> Well the person you're responding to didn't say anything like that. They're saying he's unqualified. When they said "It's the appearance of productivity, not actual productivity.", that does very much sound to me like an accusation that he is pretending or trying to deceive you into thinking he's a super productive person. > And do they work? If he's failing or fooling himself then a big chunk of his podcasting is…

> Really? I mean, let's look at some concrete examples.

That's not his most recent video, it's a fix of a 2022 video. And the channel still had pretty good output 3-4 years ago.

I compared the nickels video instead, to the worst ID system in America, and they seemed to be similar levels of embellished slideshow.

> By definition, I'm not aware of stuff he's not made public.

I thought you meant paid access stuff and it's easy to see a list of those. If you're suggesting secret videos then uh maybe but that's kind of a weird assumption.

And whatever happened with standard was too long ago to be the problem here.

> He also handles a good portion of the backend stuff for the Cortex Brand line of products (I think managing/planning logistics/inventory?).

That might be the answer but it seems like a waste of his productivity potential.

Re: OpenClaw is changing my life

#504

Post by oytis »

nbaksalyar wrote: post #332
mancerayder wrote: post #206

Earlier quoted context omitted.

Don't you get bored with spending many years learning and becoming advanced or an expert in a system paradigm (like different hosting systems), a programming language (i.e. Perl), or a framework (pick your JS framework), only to have it completely obsoleted a few years later? And then in a job interview, when you try to sell yourself on your wisdom as expert on thing X, new to Y, they dismiss you because the 25 year…

> 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…

I agree with you, but it's very hard to argue the same in an interview, even with other engineers (that's if you get the interview).

There are companies that are willing to consider general aptitude and transferable skills when hiring, but a vast majority compares candidates using checklists of technologies

Re: OpenClaw is changing my life

#505

Post by roywiggins »

causal wrote: post #496
roywiggins wrote: post #193

Earlier quoted context omitted.

I am somewhat worried that this is the moment AI psychosis has come for programmers.

Yes. Programmers might be especially susceptible precisely because our advanced understanding makes us think we cannot be easily fooled. But we are also easier to impress: only we understand how difficult it is to one-shot code a working app. AI psychosis sets in when AI captures enough of your perception to alter your reality. Programmers might be "smarter", but we give AI a bigger set of tools to capture our percep…

We are also used to prioritizing "flow states" as part of our engagement with technology, and these tools seem to be flow-state inducers. Also prone to following hype, used to typing words into computers to get results, etc...

Re: OpenClaw is changing my life

#506

Post by chickensong »

athrowaway3z wrote: post #452
chickensong wrote: post #366

Earlier quoted context omitted.

Would you describe your Claude workflow?

My agents get auto-injected with the core spec via pi-extention. I have an idea, agent turns it into a draft, depending on idea vagueness/complexity combination of: Looking for alternative, plan the change, look for alternative, split up into smaller drafts to drive separately, execute change (spec, code, tests), review change. Usually its just: Draft, plan, exec, commit. The steps are flexible enough. Usually each s…

Thanks for the write up. I'm starting to consider enhancing my setup and building on pi sounds interesting. I have a similar core workflow, but I'm still tied to CC's interface and I can see how it might be nice to have something a bit more custom.

Re: OpenClaw is changing my life

#507

Post by johnfn »

joks wrote: post #494
johnfn wrote: post #314

Earlier quoted context omitted.

It has nothing to do with power. I just want to build bigger, cooler things, faster.

It sounds more like you want to have bigger, cooler things, not build them? The joy of building is what the person you're replying to is talking about AI abstracting away

I am still getting joy out of building things. If anything, I have a bit more joy than I used to because I can accomplish small things faster. I still find the work to be mentally demanding and interesting, and there are a lot of new interesting problems to solve.

I empathize and understand that not everyone has this experience.

Re: OpenClaw is changing my life

#508

Post by worik »

viking123 wrote: post #463
torben-friis wrote: post #306

Earlier quoted context omitted.

>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 There is a counter issue though, realizing mid session that the model won’t be able to deliver that last 10%, and now you have to either grok a dump of half finished code or start from scratch.

My problem is that once I have coded a lot with the LLM, and I come across some problem that I just cannot solve with it like a synchronization issue in my game, then I have to go down to the weeds and the effort feels so gargantuan because I have mostly relied on the LLM.

That is the point. Do not lean too heavily on an LLM for code generation for that very reason.

They are still very useful, locally.

Re: OpenClaw is changing my life

#509

Post by AdeptusAquinas »

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…

It's almost as if being able to generate boilerplate code is only like 5% of software development.

That being said, its great at generating boilerplate code or in my case, doing something like 'make a react component here please that does this small thing, and is aligned with the style in the rest of the file'. Good for when I need to work with code bases or technologies that are not my daily. Also a great research assistant.

But I guess being a 'better google' or a 'glorified spellchecker' doesn't get that hype money.

Re: OpenClaw is changing my life

#510

Post by sarchertech »

brookst wrote: post #417
sarchertech wrote: post #403

Earlier quoted context omitted.

> I’ve been wanting to develop a plastic -> silicone -> plaster -> clay mold making process for years, but it’s complex and mold making is both art and science. It would have been hundreds of hours before, with maybe 12 hours of Claude code I’m almost there (some nagging issues… maybe another hour). That’s so nebulous and likely just plain wrong. I have some experience with silicone molds and casting silicone and oth…

You may just be more knowledgeable than me. For me, even getting to algorithmic creation of 4-6 part molds, plus alternating negatives / positives in the different mediums, was insurmountable. I’m willing to believe that I’m just especially clueless and this is not a meaningful project to an expert. But hey, I’m printing plastic negatives to make silicone positives to make plaster negatives to slip cast, which is wha…

I had no idea you were talking about algorithmically making molds.

You’re just talking about taking a positive 3d model and automatically creating a mold for it that you 3d print?

If so I wouldn’t want that to be algorithmic because that’s never going to work in the general case. There are just too many edge cases that you have to manually handle. Might as well just create the mold in your CAD program.

Post reply on HN