dnlgrmm

Yawn. For a moment I thought: strange that he would be tweeting such empty PR fluff. Then I realized he's at Anthropic now

As an owner of a 1700 socket mainboard and 64GB of DDR4 (recently acquired a second 32GB kit on eBay), I am very pleased to see this.

Thanks. I guess that's something you cannot easily do today.

Given my limitation with Qwen3.8-Flash of about 55t/s tg and ~1kt/s pp most of the work happening in harnesses today (around subagents, excessive use of skills, tools, huge system prompts etc.) is just not very interesting. My workflow works really well without any of it, tbh it seems more of a way to sell more tokens when you realize how much compute these techniques use to achieve modest workflow improvements.

I can really recommend running your own models to really appreciate the power and compute that goes into your prompts and tokens. Qwen3.8-Flash is good enough (Opus 4.7 level) for all of my coding needs.

Sadly this seems like introducing a very complex apparatus for little gain. I don't need MCP or many tool calls that the agent can program around - in fact the promise of pi was that you basically just need bash and no other tools. The minimally-invasive approach would have been to just "inject" tool calls as virtual bash commands. No code mode required, no hands vs. brains dichotomy. LLM can use language of its own choosing to interact with tools.