Proof of Corn

#1

Post by rocauc » Fri, Jan 23, 2026, 5:56 PM UTC

Proof of Corn
proofofcorn.com

Re: Proof of Corn

#2

Post by bstsb » Fri, Jan 23, 2026, 6:10 PM UTC

Re: Proof of Corn

#3

Post by nvader » Fri, Jan 23, 2026, 6:11 PM UTC

This is a very intriguing experiment!

I'll be following along, and I'm curious what kind of harness you'll put on TOP of Claude code to avoid it stalling out on "We have planted 16/20 fields so far, and irrigated 9/16. Would you like me to continue?"

I'd also like to know what your own "constitution" is regarding human oversight and intervention. Presumably you wouldn't want your investment to go down the drain if Claude gets stuck in a loop, or succumbs to a prompt injection attack to pay a contractor 100% of it's funds, or decides to water the fields with Brawndo.

How much are you allowing yourself to step in, and how will you document those interventions?

Re: Proof of Corn

#4

Post by divbzero » Fri, Jan 23, 2026, 6:14 PM UTC

> Want to help? Iowa land leads, ag expertise, vibe coders welcome: [email at proofofcorn dot com]

To make this a full AI experiment, emails to this inbox should be fielded by Claude as well.

Re: Proof of Corn

#5

Post by tsunamifury » Fri, Jan 23, 2026, 6:16 PM UTC

Several things about LLMs make this a hard or complex experiment and maybe too much for the current tech.

1) context: lack of sensors and sensor processing, maybe solvable with web cams in the field but manual labor required for soil testing etc

2)Time bias: orchestration still has a massive recency bias in LLMs and a huge underweighting of established ground truth. Causing it to weave and pivot on recent actions in a wobbly overcorrecting style.

3) vagueness: by and large most models still rely on non committal vagueness to hide a lack of detailed or granular expertise. This granular expertise tends to hallucinate more or just miss context more and get it wrong.

I’m curious how they plan to overcome this. It’s the right type of experiment, but I think too ambitious of a scale.

Re: Proof of Corn

#6

Post by treis » Fri, Jan 23, 2026, 6:17 PM UTC

It's cute but it seems like it's mostly going to come down to hiring a person to grow corn. Pretty cool that an AI can (sort of) do that autonomously but it's not quite the spirit of the challenge.

Re: Proof of Corn

#7

Post by qoez » Fri, Jan 23, 2026, 6:19 PM UTC

Eventually robots will do this but as long as humans do the actual irl actions it makes me think of a dystopian future where all leadership decision are made by harsh micromanaging AI bosses and low paying physical labor is the only job around for humans.

Re: Proof of Corn

#8

Post by jpmattia » Fri, Jan 23, 2026, 6:19 PM UTC

I think the most intriguing part of this effort: Farmers traditionally employ machines to achieve their harvest. Unless I'm mistaken, this is the first time that machines are employing humans to achieve their harvest.

I mean, more or less, but you see what I'm getting at.

Re: Proof of Corn

#9

Post by deathanatos » Fri, Jan 23, 2026, 6:20 PM UTC

Didn't want to have it make paperclips, eh?

(And if you read the linked post, … like this value function is established on a whim, with far less thought than some of the value-functions-run-amok in scifi…)

(and if you've never played it: https://www.decisionproblem.com/paperclips/index2.html )

Re: Proof of Corn

#10

Post by TheRealPomax » Fri, Jan 23, 2026, 6:20 PM UTC

treis wrote: post #6

It's cute but it seems like it's mostly going to come down to hiring a person to grow corn. Pretty cool that an AI can (sort of) do that autonomously but it's not quite the spirit of the challenge.

There was no challenge. There was a statement, "AI can write code, but it can't affect the physical world."