Viewing profile — 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 product…

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 proj…

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…

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 …

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 …