Hacker News Reader

Comment by MangoCoffee | Hacker News Reader

LLMs is quickly became commodities. US AI labs like OpenAI is losing their moat. Hyperscalers and data center owners who can sell cheap token will win

View on HN

I believe Codex harness is pretty sticky though I haven’t tried many others. Does anyone else provide a harness of that quality?

Their harness is indeed nice, but we're using it against our own AI Gateway at work. Right now we only expose GPT models on it, but I imagine it's possible to add our own models eventually

Pi harness with subagents is pretty great. I’m using it for everything now.

How are you handling subagents?

Usually the main agent can handle creating subagents

You say hey llm spin up some agents to do x y and z

tintinweb/pi-subagents. Then I use superpowers and it spins up subagents automatically. Works really well and you can customise the models and efforts you want to use with local AGENTS.md.

I’m primarily using gpt-5.6 and then opus for reviews.

opencode is highly regarded, I use it exclusively

I've used open code extensively -- it's not bad, but it's not anywhere near the level of the codex application.

...but we're talking about compaction, and opencode's compaction is (or was) terrible. I've seen so many horrible problems that I keep it disabled (with an envvar flag, because even the config flag to turn it off was broken).

I don't use compaction, I keep my context limited, my sessions fresh, and have agents write markdown files as needed

Open code is cool once I added the ctrl-o function to it (show thinking and command outputs at will instead of on by default), but sadly I don't think it got merged by the team.

I forgot why.

But I can't use an AI cli without that feature.

you can turn those on through the existing menu system

I have so much gratitude to the frontier companies who did all the extremely complicated research and development, model by model. It already feels difficult to remember how much capital it really took. Thank you for getting us to this point.

Reply on news.ycombinator.com