So the solution that gets upvoted during this hype cycle is the one that requires throwing more money at these companies? Curious.
Parallel AI agents are a game changer
21–30 of 88 posts
Re: Parallel AI agents are a game changer
#22Can this guy, or someone else post a full days (4-8 hours, or what ever is spent in the weeds) stream of work to youtube or something. I just want to watch the process to see what I'm missing. Or if there is anyone that already does that can they recommend it to me. I would appreciate it.
Web dev cody is great. I recommend him.
I (author) sometimes stream my work here as well https://www.youtube.com/@operatelybackstage.
Re: Parallel AI agents are a game changer
#23Context switching between more than 2 threads of work is untenable if you want to really review code in depth. And with AI, you need to go through everything with a fine toothed comb
Re: Parallel AI agents are a game changer
#24Can this guy, or someone else post a full days (4-8 hours, or what ever is spent in the weeds) stream of work to youtube or something. I just want to watch the process to see what I'm missing. Or if there is anyone that already does that can they recommend it to me. I would appreciate it.
Are you saying that because you're also skeptical? I haven't had the best time switching to agent coding. I mean for throwaway work its fine but its kind of boring and aider still messes up from time to time
Re: Parallel AI agents are a game changer
#25Obviously I'm an AI-tools skeptic, but this is hilarious: > 1. Prepare issues with sufficient context > Start by ensuring each GitHub issue contains enough context for agents to understand what needs to be built and how it integrates with the system. This might include details about feature behavior, file locations, database structure, or specific requirements such as displaying certain fields or handling edge cases.…
lmao, "good writting skills" =)
Re: Parallel AI agents are a game changer
#26Obviously I'm an AI-tools skeptic, but this is hilarious: > 1. Prepare issues with sufficient context > Start by ensuring each GitHub issue contains enough context for agents to understand what needs to be built and how it integrates with the system. This might include details about feature behavior, file locations, database structure, or specific requirements such as displaying certain fields or handling edge cases.…
>This is just software engineering?!? Absolutely. The existence of vibe coding does not mean production code is going to be engineered without the same principles we've always used - even if we're using AI to generate a lot more code than before. Any crowd suggesting that this was not the case has lost the plot, imo.
People find it a lot more palatable when the AI requires all this information than when software engineers do though. If I ask for clear requirements I’m asked to just figure it out. But if the AI implements nonsense without clear requirements that the fault of the specs.
Re: Parallel AI agents are a game changer
#27I find Codex and Claude Code to have different strength/weaknesses and wanted to be able to use them from a single interface. Currently hacking on https://devfleet.ai to make agent management more easy on myself.
Briefly mentioned on the article but async agents really thrive on small and scoped issues. Imagine hooking them up to your feedback tool (eg canny) and automatically having a PR as you review the customer feedback. Now this would likely not work for large asks but for smaller asks, you can just accept the PR and ship it really fast!
Re: Parallel AI agents are a game changer
#28Context switching between more than 2 threads of work is untenable if you want to really review code in depth. And with AI, you need to go through everything with a fine toothed comb
Yeah, I find I need to interrupt Claude at least once every two turns to prevent it from going off into the wrong rabbit hole.
Re: Parallel AI agents are a game changer
#29Context switching between more than 2 threads of work is untenable if you want to really review code in depth. And with AI, you need to go through everything with a fine toothed comb
The same work as any senior software engineer reviewing his teams work, imho.
Re: Parallel AI agents are a game changer
#30I find Codex and Claude Code to have different strength/weaknesses and wanted to be able to use them from a single interface. Currently hacking on https://devfleet.ai to make agent management more easy on myself. Briefly mentioned on the article but async agents really thrive on small and scoped issues. Imagine hooking them up to your feedback tool (eg canny) and automatically having a PR as you review the customer f…
Cool project! Do you think a lot of Codex's strengths are just from using GPT-5 as the model?