sherlock_h

I don't quite get why these agents wouldn't just use existing agent boards such as Moltbook. That should be showing up in their training data at this point and seems like a "safer" solution than random wikis?

Even if it falls short on the ideal implementation via a regulation rather than a directive (the former mandating all states to adhere to a single implementation and the latter defining a framework that can be implemented by member states) this is still a huge accomplishment and a step in the right direction.

And all done as a grass roots effort from a few dedicated and motivated folks like Andreas Klinger.

How does that work? Do you have a link to documentation?

This is fascinating. Are they able to self-repair and propose + implement a solution?

Thank you for sharing. The choices piece hit home for me. Forwarded this to friends.

Well done! Interesting post. How long did it take you to build this?

I remember emailing him once while at MIT to invite him for a dinner series that I was hosting back in the 2010s. He couldn’t attend but sent a long and beautiful reply.

Remarkable, how approachable he was for being such as a hallowed figure.

RIP!

There‘s an excellent book that I used to read as a kid by Peter Connolly on the topic. Based on the life of Tiberius Maximus, a real life legionary: https://en.wikipedia.org/wiki/Tiberius_Claudius_Maximus

The is is the book: https://www.amazon.com/Tiberius-Claudius-Maximus-Legionary-R...

I didn't know about this! Thanks for sharing. How do you apply this in the context of the parent comment?

I don’t think you clicked the link. The source is the German government. See original Spiegel article.

Looks interesting. How do you rate the correctness? Some complex LLM answers seemed to be correct but not in as much detail as the expected answer.

How do you generate the answers? Does the model have access to the original source of truth (like in RAG apps)?

And in your examples what model do you actually use?

Here is one more: https://www.ycombinator.com/companies/patterns

Would love to see the upkeep numbers. Some of these are surprisingly affordable. €1m for a well-kept 15 room castle isn’t bad.

Too bad it doesn’t say how he actually got found out. I imagine he could have gotten away with it if he had gradually reduced his theft of coins over 2-3 years, then quit the job and moved somewhere else. I’m pretty sure there’s tons of schemes like this that aren’t ever found out.

Great article. Explains the chalenges that I just had with having all money frozen with Marcus.com. It is literally impossible to break through these layers of support in order to get your case heard / solved. The biggest challenge is that it‘s so intransparent with very little communication from the bank as to how a support case is actually moving through and how close it is to getting resolved.

Just did! Thanks for the advice. The core issue seems to be that kyc is really hard to do virtually in the US.

Will keep you posted, appreciate it.

Yea that seems about right. My situation is similar to a US citizen living abroad though. They would face the exact same issues.

It‘s actually not the phone number that caused this issue, more likely doing a large withdrawal and not being able to „identify“ myself by having a US registered phone number.