lukebechtel

Fatalism is a toxic mindset. Is it hard? yes. Is it impossible? No.

I relate to this; there are some things I remember very well, but in many areas I think my talent for improvisation stems from a ~mid long-term memory.

> Chip Design

> As an early proof of concept, Kimi K3 designed a chip to serve a nano model built on its own architecture. In a single 48-hour autonomous run, K3 built, optimized, and verified the chip using open-source EDA tools on the Nangate 45nm library. Within 4 mm², the chip closes timing at 100 MHz and sustains over 8,700 tokens/s decode throughput in simulation, packing 1.46M standard cells, 0.277 MB of SRAM, and an INT4 MAC array with fused dequantization. A chip built by a model, for a model, reflects K3's long-horizon agentic capabilities.

Absolutely wild.

Some people seem to be suggesting these are coverups for quantization...

Those who work on agent harnesses for a living realize how sensitive models can be to even minor changes in the prompt.

I would not suspect quantization before I would suspect harness changes.

really fun :) thanks!

it sounds like you described it pretty well!

~/.claude/projects is where the real fun is :)

What is your domain?

so we need to make some crazy llms...

The bitter lesson strikes again, I suppose!

Good questions! It's clear I need to gather more metrics from our next generated inference library.