Live data from Hacker News

OpenClaw is changing my life

reorx.com

531–537 of 537 posts

Re: OpenClaw is changing my life

#531

Earlier quoted context omitted.

For me, getting into management was less about feeling bogged down in the specifics, but more about control (directed mostly above). Anyone who’s had a bad manager or bad decisions they need to adhere to might be familiar with the feeling that caused me to dip my toes into management. Like I’ve been in situations as an IC where poor leadership from above has literally caused less efficient and more painful day-to-day…

Asking as a fellow manager - do you ever wonder some of the people you manage might be thinking of you in the same way? Someone making terrible decisions, making them less efficient? And, have you ever noticed that something you strongly pushed back when you were an IC did not matter, or was actually the right thing in retrospect?

> do you ever wonder some of the people you manage might be thinking of you in the same way?

I'm almost certain some of those I manage do think of me in this way. I try to explain my thought process and decision making to those I manage, and I am always looking for genuine critical feedback. I also own up to it when I've made a bad call. Overall, my anonymous ratings are pretty high, and my teams have seen exceedingly low turnover so I take those as good signs.

Re: OpenClaw is changing my life

#532
post #283

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…

If you check the OpenClaw discord, a common sentiment there is "it works but only if you use Opus." That seems to be the actual situation now. Grok 4 Fast told me its own internal system prompt has rules against autonomous operation, so that might have something to do with it. I am having decent results with it though.

Edit: My bad. I investigated and... while I do think Grok does have a hidden system prompt on the API, in this case, the part about self-replication and autonomy was on OpenClaw's side!

I've noticed Claude shutting down conversations on the same subject. It says "you may continue this conversation with an older model." ChatGPT also got extremely uncomfortable talking about it, and refuses to build anything in that direction, which I find amusing since its ancestor GPT-4 built a self-modifying Python programmer in 2023.

(Also, OpenClaw meets GPT-5's definition for "extremely dangerous AI software" due to the self-modification factor. But I think that applies trivially to any agent, so...)

Re: OpenClaw is changing my life

#533
post #250
post #165

I have always failed to understand the obsessive dream of many engineers to become managers. It seems not to have to do merely with an increase in revenue. Is it really to escape from "getting bogged down in the specifics" and being able to "focus on the higher-level, abstract work", to quote OP's words? I thought naively that engineering always has been about dealing with the specifics and the joy of problem solving…

As an engineer, I can never actually let a system write code on behalf of me with the level of complacency I've accumulated over the years. I always have opinionated design decisions, variable naming practices. It's memorable, relatable, repeatable across N projects. Sure, you can argue that you can feed all this into the context, but I've found most models to hallucinate and make things unnecessarily opaque and comp…

I've started collecting all my opinionated practices in a file I call ENGINEERING_PRINCIPLES.md, which I share across all my projects and reference in every CLAUDE.md. It contains variable naming practices, rules of thumb for writing good code comments, guidelines for unit & integration tests, general architectural principles (avoid global state & push side effects to the boundary aka "functional core, imperative shell", avoid Java enterprise-style OOP hell, etc.), …

So far, the code Claude has generated looks fairly decent and stylistically not too different from what I would write myself.

Re: OpenClaw is changing my life

#534

Earlier quoted context omitted.

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…

For me the biggest benefit from using LLMs is that I feel way more motivated to try new tools because I don't have to worry about the initial setup. I'd previously encountered tools that seemed interesting, but as soon as I tried getting it to run I found myself going down an infinite debugging hole. With an LLM I can usually explain my system's constraints and the best models will give me a working setup from which…

great point. llm breaks that initial fatigue where to start if you go outside of your comfort zone tech stack

Re: OpenClaw is changing my life

#535

Earlier quoted context omitted.

You have to be joking. I tried Codex for several hours and it has to be one of the worst models I’ve seen. It was extremely fast at spitting out the worst broken code possible. Claude is fine, but what they said is completely correct. At a certain point, no matter what model you use, llms cannot write good working code. This usually occurs after they’ve written thousands of lines of relatively decent code. Then the p…

I beg to differ, and so do a lot of other people. But if you're locked into this mindset, I can't help you. Also, Codex isn't a model, so you don't even understand the basics. And you spent "several hours" on it? I wish I could pick up useful skills by flailing around for a few hours. You'll need to put more effort into learning how to use CLI agents effectively. Start with understanding what Codex is, what models it…

I’ve been using models just fine for months now. Codex is terrible, full stop.

Re: OpenClaw is changing my life

#537
Same experience. The productivity gain is real. The one thing I couldn't solve: using it with a team. Who can use which agent? What can each agent access? Started building Pinchy (https://heypinchy.com) — enterprise layer on OpenClaw with RBAC and audit trails. AGPL, Docker Compose. (Disclosure: I'm the builder.)
Post reply on HN