I've been daily driving Pi for over a month now and never looking back. The latest crop of frontier models have really complex bash calls, so I've written an extension that rewrites them into plain English while still making them easy to reveal in full, unlike some harnesses which seem to try to hide this from the user which is pretty irresponsible IMO.[0]

[0] https://github.com/siraben/pi-tool-summaries

▲

alex_duf a day ago | parent | next [-]

I just have custom instructions to tell the model to edit files using its tools rather than a gigantic bash pipelines. That's 80% of it.

▲

siraben a day ago | parent | next [-]

I prefer not the fight the RL as the models get better, unless I've measured it and haven't observed any degradation. There may be other costs/no. of turns considerations too.

▲

machomaster a day ago | parent | prev [-]

Would that be useful in other harnesses/models like Codex? Wouldn't that lead to increased token usage?

	▲	alex_duf 6 hours ago \| parent [-]
		I assume it works with any harness. Frontier models have been pushed to reduce their token usage so much that they got to be creative and use bash CLI to edit files, which achieves the goal of reducing token usage but makes reading the traces less practical. It's a trade-off. Personally I like occasionally re-reading the edits and I prefer use more tokens and understand what's happening (or have the illusion to understand).

▲

lifeisloving a day ago | parent | prev | next [-]

I just have a hook that tells agents to echo what they're trying to do. Works fine.

▲

someothherguyy a day ago | parent | prev [-]

alternatively, you could learn to read it

	▲	siraben a day ago \| parent [-]
		The rewrite is configurably off for bash/tool calls below a certain line length. I would prefer not to read codegolfed bash and python for hours every day, personally.