Hacker News

points by thefourthchime 3 days ago | 0 comments

It used to be more interesting and elaborate, switching between different models. I used to use Cursor, then Codex, but since Opus 5.5 came out, I just use the Claude IDE. I got rid of all my skills and just set it to medium. Then I vaguely talk to it about very high-end things that I want, and it comes back with magic. Rinse and repeat.

I'd say the biggest trick is just to tell it what complete looks like. Be very specific about what you want it to come back with once it's done. That gives it a good idea what the goal is. It'll automatically create subagents and all that stuff. Although if you have money to burn and you're doing something large, you can tell it to just go wide or boil the ocean.

Also, make sure you're working on at least five different things. Otherwise, you're sitting around for one agent.

[–] fhub 3 days ago

I can do 5 things concurrently for about a day max. 3 things concurrently all week and my weekends are spent untangling my brain. 3 things per day on Mondays and Tuesdays and 2 things per day concurrently on Wed-Fri and I feel ok but crave holidays.

[–] thefourthchime 3 days ago

I probably have some kind of pysccosis. I've had a personal $200 plan from one of the AI providers since March 2026. I'm never not making things now, I haven't rebooted my laptop for weeks because there is always an agent building something.

I cycle between 4-5 work projects and 2-3 personal projects. Every night I tell me agents I'll be going to bed and to not ask questions and keep going. I've always loved building things, but this feels more like an addiction than healthy sometimes.

They're not all done, and half the projects I bench, but this is where my personal projects live. https://wooten-labs.com

[–] networkbug 2 days ago

not gonna lie, you don't need to be doing these projects. they're not really worth it. instead of building an app to help you meet up with your friends somewhere central just go meet up with them and explore together.

[–] vidarh 2 days ago

I don't need to be doing all of these projects, but I enjoy doing all of these projects, much more than I enjoy going somewhere to hang out with people. Not everyone is the same.

[–] senordevnyc 2 days ago

Eww, gross. Don't be rude.

[–] senordevnyc 2 days ago

Just to be clear, my comment about this being gross is about the rudeness of telling someone else their hobby is a waste of time, not about hanging out with friends.

[–] fishtoaster 2 days ago

> I haven't rebooted my laptop for weeks because there is always an agent building something.

I'm pretty pilled on cloud agents these days. If I've got 5 agents going at once, each is in their own dedicated, isolated cloud environment. There are a bazillion services for this now ampcode, hoplite.sh, cursor's cloud agents, devin.ai cloud, and more.

I haven't had an agent do anything from my laptop in a month or two.

[–] KronisLV 2 days ago

> Every night I tell me agents I'll be going to bed and to not ask questions and keep going.

Most harnesses now support something like this:

  /goal "Work on the current plan until 11 AM in my time zone, provide a summary of all the overnight work then."

Other than that, look after your own wellbeing! Nothing wrong with letting agents work overnight, just don't overextend yourself and don't spend all of your free time on it.

[–] chasd00 2 days ago

My friend and I have built portfolio management agents and pit them against each other to see who can make the most money (not real money just a simulated bank account and stock portfolio). So mine runs every morning to read the news and do analaysis and all that. I have it write a daily blog that I read to keep track of what it’s doing.

A daily blog for status and reasons for decision making works pretty well for tracking an agent that works unattended. It’s also kind of funny when it writes things like “well I got that one wrong” and “this is not what I expected to happen” hah

[–] perforator 2 days ago

How long have they been running for and do any of them consistently beat index funds? Was always curious about the idea, but thought the market would already price it in.

[–] chasd00 2 days ago

They've been running for a few months, my friend's was beating SPY (VSP500) for a few days but not any more. Mine never beat SPY or VOO (Vanguard SP500 index). Now, let me tell you about my little sister. She says she just does what ChatGPT tells her to do and she's #1 on the leaderboard beating everyone including the SP500.

stewbot-v1 = my friend's bot

stonker = my bot

https://stonks.jettdigital.app is my little vibecoded stock market sim website, the bots work with via API. Each account starts with $10k and then you get a $500 deposited each month. If you want an account drop me an email ( see my profile ).

here's my bot's page with the daily posts (the key is like a password but it's no big deal, if my server catches fire i'll just change it). Link to the daily posts are at the top left https://stonker.jettdigital.app/?key=a87f2427bf1e281dda1a513...

[–] rootusrootus 14 hours ago

There are so many quants working 24x7 to eek out any advantage they can in the market, it's basically noise. If you want to algorithmically (or using AI) gain an advantage in market, pick a smaller one, like a niche betting market of some kind, that isn't overrun with other actors already doing it.

[–] abhishekbasu 2 days ago

love the website, but quality control is important when working with these agents.

ex. i tried cool walk (https://wooten-labs.com/coolwalk) and the 'Download on the App Store' does nothing at all.

[–] thefourthchime 2 days ago

It's been waiting for App Store for a long time. Things take forever to get accepted now.

[–] gausswho 2 days ago

I like your landing page for Stealthbox. Playful and stylistically distinct. Wears its AI generated origins with casual pride.

I do wish the Github link wasn't borked.

[–] thefourthchime 2 days ago

Yeah, I've been working on this thing for months. I'm trying to get it more polished before I release it. The reason the GitHub link is borked is because I need to have part of it be private, because some of the bot detection can't be open source, or it'll stop working.

Eventually I'll stop finding bugs : )

[–] themoose8 2 days ago

They look like awesome apps*, as long as you're balancing your time by using them (they're outdoorsy and social!) I'd say you're doing fine. Take some extended time off if you need!

*unfortunately I'm android

[–] petesergeant 2 days ago

> I haven't rebooted my laptop for weeks because there is always an agent building something

I have a cheap mini PC I use as a devbox. Beyond meaning I can close my laptop and close all agent windows, it also keeps agents out of my personal shit.

[–] LittleBox 1 day ago

You are going to burn out so badly and you won’t even realize it until it’s too late.

[–] coffeesoda 2 days ago

respect. this is how i've been working the last 4 months or so. it's a bit crazy making and i do think i'm enjoying things less because i'm preoccupied, but i sure do feel productive. lol.

[–] Fervicus 2 days ago

At least you are self-aware.

[–] willchis 2 days ago

That's a really nice website!

[–] abrookewood 3 days ago

Nice website :)

[–] bkaae 2 days ago

I hope you are doing okay bud, sounds like you are doing too much.

[–] jeffyaw 2 days ago

cool visuals on your site! dig the scroll down!

[–] pavas 3 days ago

Honestly it does sound like an addiction. Touch some grass...

[–] glennfiedler 3 days ago

> I probably have some kind of pysccosis

No you don’t. You are doing everything right :)

[–] glennfiedler 2 days ago

I have no idea why anybody is downvoting this. I honestly believe the OP is doing it right. Very few people get this level of productivity out of AI and the people who really "get it" with AI have this strong attraction to it. I estimate, fewer than 5% of programmers working with AI ever get here.

[–] biggestriverman 2 days ago

I had the same issue. What you need in a management system for your claude sessions.

[–] fhub 2 days ago

The problem is that I do want to interrogate the planning and implementation. Ask questions about trade offs. That means context switching. I don’t want my knowledge of the system to degrade rapidly.

[–] thefourthchime 2 days ago

I tried a T3 code for a hot second, but found it too buggy and missing features I missed from Claude Code Desktop. I do desperately need to figure out some way to get stuff off my laptop.

[–] sparklingmango 3 days ago

I firmly believe that those using out-of-the-box Claude Code or Codex are likely getting the most cutting edge features of agents anyways.

[–] 0x4e 3 days ago

I’m a user of both and don’t really see the need to go anywhere else. It all just sounds like mumbo jumbo.

As a solopreneur of a boring SMB.

I still do coding and build my own tools but I don’t see the need for agent swarms or Muse or Grok Bot or any of that.

The reason why I stay away is because I like to do QA on the slop these things generate. Having them run amok just makes me nervous.

[–] jeffyaw 2 days ago

and you can get a modest swarm with subagents and ultracode.

[–] 2001zhaozhao 3 days ago

Yep, Claude & Codex desktop are innovating extremely rapidly. Some of the features like code review are hidden under commands, but basically obsolete whole heaps of AI code review startups when you use them.

[–] smashed 3 days ago

I just ask Claude code to do a code review of PR X and it spawns a sub-agent. No hidden commands or anything special.

If I hint it might be security sensitive code, it bumps the effort level and burns my usage.

But it works quite well.

The findings are often debatable or unreachable states but it does find stuff and improves the overall quality I find.

What's funny though is that it almost always inevitably finds something wrong, even if you just ran it in another window and fixed everything it found. There is really a point of diminishing returns.

[–] chasd00 2 days ago

For anything non trivial I have Claude do a design doc with me. Then I tell it to “carefully review” the design which turns up edge cases. Then I tell it to make a step by step implementation plan document. Then ask it to review both again. Then I do a personal review and then off it goes on implementation while I pull up HN. It’s a lot like my team lead role at work. Btw, people who have a few years of being in a TL role are best positioned to make full use of the agents as well as teach others how to get the most out of them.

[–] bluerooibos 3 days ago

> Claude IDE

Claude Desktop's UI seems pretty similar to Cursor now, almost. I'm still on Cursor but if I use it daily I often hit usage limits before the end of the month. Would you say using Claude directly is better bang for buck?

[–] senordevnyc 2 days ago

I switched from Cursor to Claude Code (via T3.codes) because I was running out of usage on Grok 4.7. I regret not making the switch sooner, Opus 5.5 is much better than Grok, and Grok is decent!

[–] bluerooibos 1 day ago

Yeah, I agree, but Opus 5.5 burns through a ton of usage in Cursor so I rarely use it. Just wondering if cost wise it's better to use Claude Code than Cursor w/ Grok - sounds like you think it is?

[–] senordevnyc 1 day ago

My $200 Anthropic subscription is giving me way more value than my $200 Cursor subscription was.

[–] onion2k 2 days ago

Same journey for me, although I still use skills. Claude Code is fine; the remote-control feature is why I stick with it now. Generally anything in the cloud doesn't have a proper GPU that supports WebGPU, and as nice as SwiftShader is often you want to actually run things on a real machine. remote-control is by far the easiest way to do that from my phone.

[–] bartread 2 days ago

> I got rid of all my skills and just set it to medium.

Yeah, exactly. I find increasingly little use for skills. I'd put it down to switching projects and stacks a lot but maybe... they just aren't as useful any more?

[–] parkersweb 2 days ago

I wasn’t really using skills but then our project management tool added an MCP so I made a skill for grabbing tickets from the backlog, creating worktrees with the right naming convention, and moving ticket states for me automatically.

At the same time when I’m exploring new feature requests I now use the skill to write up the requirements and estimates into as many tickets as needed.

Massively changed my workflow for me.

[–] darklinear 1 day ago

I find I am able to get rid of most of the skills just by listing out the style guides the bot should follow in AGENTs.md

[–] jeffyaw 2 days ago

any prompt that you’re running a lot, make it a skill. i don’t make a lot of new ones. but still am using ones i made months ago and have been refining.

[–] persavon 3 days ago

What do you mean by Claude IDE?

[–] thefourthchime 3 days ago

Claude Code Desktop. https://code.claude.com/docs/en/desktop

[–] neuronexmachina 3 days ago

Yeah, I used to hate the Claude desktop app's Code tab, but it's actually pretty good nowadays. I actually prefer it now over claude CLI.

[–] iainmerrick 2 days ago

I use Claude Code Web almost exclusively for personal projects -- I’m guessing that’s pretty much the same interface but in the cloud -- and hardly ever run anything locally. Nicer UI than a terminal, real sandboxing, and it doesn’t tie up my computer. It’s just a remote agent that can make GitHub PRs.

[–] OJFord 2 days ago

But even worse for private stuff than using cloud inference to begin with, since it presumably has to clone the repo, have write & Actions access back, etc.

[–] iainmerrick 2 days ago

It's bad if you're concerned about your data being used for training, sure. But I don't think any worse than e.g. running Claude or Codex locally.

I think the only solution there is self-hosted inference (either local, or on your own cloud servers with open weights).

[–] OJFord 2 days ago

That's the bit that's common, I say it's worse because it has to actually check out the full source on their server. i.e. similar to if you used Claude locally, plus used third-party CI like Circle instead of Actions.

[–] yuppiepuppie 3 days ago

Yeah I was thrown off by that as well. I assume they mean just Claude TUI..

[–] sabas123 3 days ago

I have a similar story as OP, for me its the Claude Desktop, not claude code.