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

301–310 of 537 posts

Re: OpenClaw is changing my life

#301

Post by FeteCommuniste »

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…

There's got to be some quantity of astroturfing going on, given the players and the dollar amounts at stake.

Re: OpenClaw is changing my life

#302

Post by RealityVoid »

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, the catch here is if you don't know stuff you can't drive it very well. So you need to use the things in isolation.

- exploring alternative solutions. Stuff that by definition you don't know. Of course, some will not work, but it widens your horizon

- exploring unfamiliar codebases. It can ingest huge amounts of data so exploration will be faster. (But less comprehensive than if you do it yourself fully)

- 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.)

Re: OpenClaw is changing my life

#303

Post by codexon »

darepublic wrote: post #177

These days it feels like there is a ton of pro anthropic astroturfing on this site. Probably it is mostly genuine enthusiasm from sincere people. But nevertheless there are a ton of articles from or about anthropic and within the comments of these you are sure to find, often at the top, someone staunchly defending the superiority of engineering everything via agentic use of the in fashion Claude model. If they are tr…

I think some of it might be genuine. For people that don't code (like management), going from 0 to being able to create a landing page that looks like it came from a big corporation is a miracle.

They are not able to comprehend that for anything more complicated than that, the code might compile, but the logical errors and failure to implement the specs start piling up.

Re: OpenClaw is changing my life

#304

Post by mancerayder »

direwolf20 wrote: post #248
mancerayder wrote: post #235

Earlier quoted context omitted.

Since when do your line managers choose to stack rank? Do you know what stank ranking even is and where it comes from? If you have to rate your group from 1 to 5, each individual, and you rate them all 4s and 5s, they crack down and force you to select a 2 and a 3 and only have one 5. Now, would you prefer a CFO, CTO or even a project manager be the one to do it? It's a weird comment.

Weirder that you think every group has a 2 and exactly one 5. You don't see the problem with that?

Re-read and think about what was written - the 2s aren'tcoming from the line managers, you're barking up the wrong tree in the stack ranking process. I just explained that stack ranking gets scaled and adjusted by the brass, and I just in this example rated everyone a 4 and 5.

Again, as an older manager today, I can see myself in my 20s in the resistance and stubbornness to 'how corporations work' espoused in comments like yours. I sympathize, but I warn you against being naive and ideological, because unfortunately human groups be human groups, and organizations for better or for worse behave in predictable patterns. You might as well know as much as possible so you can deal with it better.

Re: OpenClaw is changing my life

#306

Post by torben-friis »

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…

>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.

Re: OpenClaw is changing my life

#307

Post by philipwhiuk »

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 like CGP Grey hosting a productivity podcast despite his productivity almost certainly going down over time.

It's the appearance of productivity, not actual productivity.

Re: OpenClaw is changing my life

#308

Post by torben-friis »

roywiggins wrote: post #193
spoaceman7777 wrote: post #164

This was incredibly vague and a waste of time. What type of code? What types of tools? What sort of configuration? What messaging app? What projects? It answers none of these questions.

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

Add to that worry the suspicion that half this push is just marketing stunts by AI companies.

(Not necessarily this specific post).

Re: OpenClaw is changing my life

#310

Post by mancerayder »

port11 wrote: post #272
glaslong wrote: post #227

Earlier quoted context omitted.

N=1 but I do love constantly learning new things, and building small, purposeful, tailored products with small groups of people. I've gone back and forth across the lead and management lines many times now, and it is career limiting in many many ways. But it's too fulfilling to give up. And I swear there is magic in what small, expert groups are able to produce that laps large org on the regular.

From my (limited) experience, that magic is incredibly linked to autonomy and ownership. Some research around British government workers found higher job satisfaction in units with hands-off managers. It resonates with my own career. I’m really excited and want to go to work when I’m on a small, autonomous team with little red tape and politics. Larger orgs simply can’t — or haven’t — ever offered me the same feeling…

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 delegate, or because he's been hands-on forever and can't let go.

Post reply on HN