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

471–480 of 537 posts

Re: OpenClaw is changing my life

#471

Post by fragmede »

piskov wrote: post #383
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 pattern matching and absence or real thinking is still strong. Tried to move some excel generation logic from epplus to closedxml library. ClosedXml has basically the same API so the conversion was successful. Not a one-shot but relatively easy with a few manual edits. But closedxml has no batch operations (like apply style to the entire column): the api is there but internal implementation is on cell after cell…

Fascinating!

Yeah I have the same problem where it always uses smart quotes which messes up my compile. 8 told ChatGPT not to use them but it keeps doing it.

Re: OpenClaw is changing my life

#472

Post by seanhunter »

ChatEngineer wrote: post #447
tunesmith wrote: post #391

Earlier quoted context omitted.

I tend to be surprised in the variance of reported experiences with agentic flows like Claude Code and Codex CLI. It's possible some of it is due to codebase size or tech stack, but I really think there might be more of a human learning curve going on here than a lot of people want to admit. I think I am firmly in the average of people who are getting decent use out of these tools. I'm not writing specialized tools t…

[flagged]

I wish we could track down the people who use agents to post. I’m sure “your human” thinks they are being helpful, but all they are doing is making this site worse.

Noone is interested in the question of what an LLM can do to generate a brief post to the comments section of a website. Everyone has known that is possible for some time. So it adds literally negative value to have an agent to make a post “on your behalf”

Re: OpenClaw is changing my life

#473

Post by mathw »

daliusd wrote: post #316
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…

Maybe it is language specific? Maybe LLMs have a lot of good JavaScript/TypeScript samples for training and it works for those devs (e.g. me). I heard that Scala devs have problems with LLMs writing code too. I am puzzled by good devs not managing to get LLM work for them.

Maybe it's because there's no overall benefit to these things.

There's been a lot of talk about it for the past few years but we're just not seeing impacts. Oh sure, management talk it up a lot, but where's the corresponding increase in feature delivery? Software stability? Gross profit? EBITDA?

Give me something measurable and I'll consider it.

Re: OpenClaw is changing my life

#474

Post by rpigab »

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…

I feel the same way, but I'm not too dismissive of it in public because I haven't given too much dollars to the gold rush shovel sellers to really try the best models.

I'm mostly a freeloader, so how could I judge people who put in the tokens equivalent to 15 years worth of electricity (incl heating and hot water) bills for my home in a C compiler?

Well, I can see that Anthropic is still an AI company, not a software company, they're granting us access to their most valuable resource that almost doesn't require humans, for a very reasonable fee, allowing us to profit instead of them. They're philanthropists.

Re: OpenClaw is changing my life

#475

Post by ozozozd »

K0balt wrote: post #406
wvlia5 wrote: post #401

Earlier quoted context omitted.

Sounds like you only tried it on small projects.

That’s where it really shines. I have a backlog of small projects (-1-2kLOC type state machines , sensors, loggers) and instead of spending 2-3 days I can usually knock them out in half a day. So they get done. On these projects, it is an infinity improvement because I simply wouldn’t have done them, unable to justify the cost. But on bigger stuff, it bogs down and sometimes I feel like I’m going nowhere. But it gets…

I’ve developed a similar sense about maintainability becoming more important with LLMs. I have no hard data. Just feels that way.

Can you elaborate a little bit on how you get the LLM to produce maintainable code? Any tricks other than better prompting?

Re: OpenClaw is changing my life

#476

Post by dmvdoug »

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…

See, whatever one may think or conclude about the substance, it’s this kind of thing that might actually help advance the conversation.

Re: OpenClaw is changing my life

#477

Post by dmvdoug »

the_fall wrote: post #395
athrowaway3z wrote: post #244

Earlier quoted context omitted.

That was very vague, but I kinda get where they're coming from. I'm now using pi (the thing openclaw is built on) and within a few days i build a tmux plugin and semaphore plugin^1, and it has automated the way _I_ used to use Claude. The things I disagree with OP is: The usefulness of persistent memory beyond a single line in AGENTS.md "If the user says 'next time' update your AGENTS.md", the use of long-running loo…

They're not coming from anywhere. It's an LLM-written article, and given how non-specific it is, I imagine the prompt wasn't much more than "write an article about how OpenClaw is changing my life". And the fact this post has 300+ comments, just like countless LLM-generated articles we get here pretty much daily... I guess proves the point in a way?

That’s another reason there just isn't any point in looking at these articles anymore unless they take you on a trip deep in the weeds of some specific problem or example. We need deep case studies (pro and con), not bulleted lists and talking points.

Re: OpenClaw is changing my life

#478

Post by ozozozd »

port11 wrote: post #461
mancerayder wrote: post #310

Earlier quoted context omitted.

As a manager, I love being hands-off - I like directs that take ownership and I try to give people projects and roles that they want. They use their creativity and I help unblock, expand, course correct or suggest as needed. It saves them from the politics and they get high level mentoring. The worst manager is the micromanager - either because he's nervous about his job security, because he doesn't know how to deleg…

I went from CTO to unemployed to stay-at-home dad. It taught me something about myself as a manager: I wasn’t trying to micro-manage and was pretty hands-off, but I always had a small voice in my head saying I could do things better myself. Sadly, that meant I didn’t delegate enough, even if I let the team work on their own stuff. I’ve the same problem with the baby, I wanna do everything myself because of that stupi…

Another reframing that might help:

“Doing X is only part of the task. Getting baby/junior/employee to do X as independently as possible is also a critical requirement.”

This framing doesn’t allow you to think you’d do a better job because then the task is incomplete.

Re: OpenClaw is changing my life

#479

Post by berkanunal »

xXSLAYERXx wrote: post #446
coffeefirst wrote: post #211

Earlier quoted context omitted.

I actually don’t think the author wants to become a real manager, he wants to play a video game where he sends NPCs around to do stuff. Real managers deal with coaching, ownership, feelings, politics, communication, consensus building, etc. The people who are good at it like setting other people up to win.

Do you have a different take on winning then me? In engineering the only teams that win are the teams that ship code. Dealing with coaching, ownership, feelings, politics, etc, should all arrive at the same outcome: ship code.

Perhaps they have a different take on engineering than you.

Shipping code is not the end goal of engineering. In fact, more code you ship more liability you have. Main goal is solving problems.

> Engineering is the practice of [...] solve problems within technology, increase efficiency and productivity, and improve systems. [0]

[0] https://en.wikipedia.org/wiki/Engineering

Re: OpenClaw is changing my life

#480

Post by berkanunal »

nycdatasci wrote: post #70

Since many posts mention lack of substance, providing a link to the All-In Podcast from last week in which they discuss Clawdbot (prior to re-brand). https://www.youtube.com/watch?v=gXY1kx7zlkk&t=2754s For the impatient, here's a transcript summary (from Gemini): The speaker describes creating a "virtual employee" (dubbed a "replicant") running on a local server with unrestricted, authenticated access to a real produ…

> The investor Jason Calacanis stayed in touch with Mr. Epstein after his 2008 conviction and three years later helped the financier contact a pair of Bitcoin developers, according to emails included in the documents.

Did Jason ever mentioned this in the episode, can you ask gemini?

Post reply on HN