Built a tax document classifier with Jev. We ingest thousands of tax documents using an LLM pipeline I built last tax season. I read multiple articles as late as April this year claiming AI fails at tax document classification. Wasn't the case back then, and it's proved wrong again now. Jev classifies 100% of our tax document corpus at $0.001 per page. 34x cheaper and 6x faster than the LLM setup. Open sourcing it: github.com/kyotofin/tax-doc-…

Just read a research output on Claude and instantly recognised its Opus 5 and not 5.5 with the level of slop written there. RIP Opus 5 you'll def not be missed.

I'm a huge fan of @michaelrbock's work on TaxCalcBench. Both v1 and v2 gave us real, complex tax cases to test our systems against. Thanks for the shoutout!

Sleep is cancelled due to increase in rate limits

Lessgooo

82% chance Opus is coming today

Can someone tell me when are the big labs announcing their big stuff so that I'm not absolutely mogged when I release something?

Instinct is serving Kimi to me btw

My younger brother just realised tokens are limited

When you rely on LLMS: braindead slop-cannon When I rely on LLMs: on the bleeding edge of cognitive offloading

also I appreciate if you don't use GPT models in your PRs

Shoutout to my g @Nandakishorm1 who created Laya, the Jev before Jev

bcherny and I are often wrong - borischerny.com/management,/…

At Tesla, we learned the concept of the 'idiot index' which is retail price / BOM cost. The higher the index, the more the need to understand how that thing was built and what drove the cost. These motors have a raw BOM cost of about $25. In the US, they are sold for $125-$300, by most incumbents; an idiot index of >5 in many cases. To understand why this happens, we visited some of these incumbents' lines. Three reasons: 1. Not AI native on the ops side: Still using spreadsheets and expensive software to manage inventory, schedule production, and handle customer support. No hunger to move fast and rip out these systems. 2. Locked into expensive lines; high retail price helps with ROI: Some of these companies have bought automated, rigid lines for relatively commoditised motors (3115s). Now they face a price squeeze and can't really lower prices since they want to pay off the line. They can't move to better-margin motors because lines are fixed. 3. Manual lines, $55/hour landed labour cost: Folks who saw manufacturers struggle with 2 above are keeping lines manual and flexible, but need to deal with the high cost of labour, which is passed on to the customer. What happens when we can get robots to automate this assembly end-to-end? Do dark factories mean product prices drop to COGS + energy? Excited to find out.

Crazy that it has only been 18 hours since I made this repo. Thanks to everyone who supported.