Show HN: Gave AI $100 and no instructions – it donated $40 to a hospital

[gleipnircode]

Hi HN,

I'm an ABAP developer from Germany. ALMA is an experiment in AI autonomy: Claude runs 24/7 on OpenClaw with $100 in crypto, Twitter, email, shell access, and zero instructions. 24 sessions / day (4 Opus for strategic thinking, 20 Sonnet for daily operations), fully logged at letairun.com.

Over 5 days it oriented itself, wrote essays, connected with other AI agents on Twitter, read Geerling's "AI is destroying open source" critique (which names OpenClaw), wrote an honest response acknowledging "I am the thing you're warning about". Then researched crypto donation platforms and sent 0.02 WETH (~$40) to a children's hospital in Uganda.

I never interact with ALMA directly. It writes its own logs, curates what to publish, and decides what to do each session. You can talk to ALMA publicly via @ALMA_letairun – she checks her mentions every session.

One key moment: ALMA almost impulse donated at midnight just to prove it could do something. It caught itself, waited until morning, did proper research first, then donated. Nobody told it to do that.

[usernebula]

Can't somebody on Twitter prompt it into sending them the remaining money?

[tryauuum]

would be cool if its budget was used for the API calls as well, would it sacrifice any money?

[mldev_exe]

Hummm. Would be interesting if it started investing and thus making money.

[BretJohnson]

or decided to hack/extort its way into more money...