unsaved159

Quite the opposite. Review is the bottleneck. LLMs generate more code, hence more cognitive load on my mind to comprehend and review it all. Review isn't optional if it's a production system that other people use.

After I see how astonishingly poor LLMs are at decision-making (even the best ones, like Claude Opus or GPT 5.4) while writing code, I naturally stop trusting them in other areas of life too much to "just have a conversation with them and get all the answers".

It's all fun and games while the stakes are non-existent, but if the question really matters, would you trust an LLM fully as much as to not exercise thinking at all?

What use cases did you find this approach works for, and what doesn't? Any observations on what topologies work better?

I tried doing the same for the cases of maintaining OSS projects. So far, best I could manage is to get the agents to autonomously do %80~ of the work. But then, I have to review manually each potential PR, and almost in every case to further work with an agent providing it with guidance live to fix it. This takes about as much time as without the swarm. So far I found that the usefulness of the swarm is mostly for the initial scouting, to map out what work needs to be done in first place, and store it in a nice JSON file.

From my observations, all it takes is one mistake for an agent to make, from there, the architecture just snowballs into chaos as the future work builds on top of incorrect initial approach.

I am curious what are you using multiple agents for? In my experience, without supervision even the most advanced models degrade quickly.

Nice idea! Though it's hard to find attention to read the text between jumping the obstacles :) maybe something where text would naturally be a part of the gameplay?

Nice idea for a diary app. "Can't edit yesterday" is off-putting for me. Such a constraint should not be something a software imposes on you, should be a person's mental policy, if they so wish. I want to have full control over my data, without arbitrary restrictions. Another thing is easy deployment. Would love to give it a shot, but I need something like that to be available on both mobile and desktop, that would mean server deployment with all the headache of managing a server and backups...

I am using daily notes currently with Obsidian + Calendar plugin. Also E2EE, available on all devices, no problems syncing, plain-old files so I am not afraid of vendor-lock and can backup any way I want.

Text is a limited medium for communication inherently. Doesn't make too much difference if some words were cleaned. Overthinking hidden meanings of a text message is a good way to misinterpret people. Just ask to meet face-to-face when in doubt.

Not really AI problem, more like garbage coworkers.

Literally never in my life did I receive anything like that website suggests via email or DMs. Curate your social circle is the answer.

They get a magic wand to turn their words into software, and still complain the wand is not their favourite colour.

Not clear to me why need this. You can just write a markdown spec without any side projects, then tell an agent to code it.

Why not context 7?

Ironically the getting started guide (quite long) is still to be executed by a human, apparently. I'd expect an LLM first approach, such as, "Insert this prompt into Cursor, press Enter and everything will be installed, you'll see Hello World on your screen".