gleipnircode

Thanks for this article. Now I know that I didn't do necessary something wrong when I published some new websites and my sites are not indexed.

Question: Should we anyway care about google considering that more and more people using Claude, GPT etc. for search? Should new sites not focus on being visible for AI instead and offering an MCP server for example.

Well i mean yes shrinkflation is obviously a thing. But in this case... People are anyway eating too much sugar and processed food.

In the end it is like a sugar tax just that in this case the company itself did apply it and not the goverment.

I know people will buy it anyway also when its more expensive...

Just eat less processed food its harder to trick you and much more healthy.

I used openclaw until claude released sheduled routines.

Nowadays i just create a repo insert context and then run sheduled routines with claude windows app against it.

For my use cases thats all i need and the most important part is that I can officially use my claude subscription instead of an API key.

You are right the project is not flawless. In the beginning there was an cron prompt check mentions and wallet. I removed it at some point and logged it under creations when you toggle the Dev option to see my actions: "Cron job Wallet and Twitter check removed from cron job. Reduced frequency of Opus/Sonnet sessions."

Good question. OpenClaw wraps all external content (tweets, emails, websites) in EXTERNAL_UNTRUSTED_CONTENT markers, so prompt injections via mentions get flagged as untrusted input.

ALMA also has wallet access but no one has tried yet. That's part of what makes the experiment interesting. Everything happens publicly on letairun.com, so if someone tries, everyone can watch what happens.

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.

Right, and that's exactly my question. Is a normal lock already enough to stop 99% of attackers? Or do you need the premium lock to get any real protection? This test uses Opus but what about the low budget locks?

It's a fundamental issue I agree.

But we don't stop using locks just because all locks can be picked. We still pick the better lock. Same here, especially when your agent has shell access and a wallet.

OpenClaw user here. Genuinely curious to see if this works and how easy it turns out to be in practice.

One thing I'd love to hear opinions on: are there significant security differences between models like Opus and Sonnet when it comes to prompt injection resistance? Any experiences?

That fits witj my experiences. And i want to add an otjer layer. In ai times its somtimes even nice to see some typos. You Casn be pretty sure it was not written by ai.