Did you read my comment?

Skimmed the repo, this is basically the irreducible core of an agent: small loop, provider abstraction, tool dispatch, and chat gateways . The LOC reduction (99%, from 400k to 4k) mostly comes from leaving out RAG pipelines, planners, multi-agent orchestration, UIs, and production ops.

Hetzner is definitely an interesting option. I’m a bit scared of managing the services on my own (like Postgres, Site2Site VPN, …) but the price difference makes it so appealing. From our financial models, Hetzner can win over AWS when you spend over 10~15K per month on infrastructure and you’re hiring really well. It’s still a risk, but a risk that definitely can be worthy.

Twitter is heavily moderated, in bad ways. Can you say "cisgender" yet?

I think there's a non-trivial probability that concern over social media is a moral panic, and it's being used as a scapegoat for larger social forces. I wonder if much of what it does is surface our neuroses and issues into public, and thus here we are only shooting the messenger.

This may prove out if after 5yr+ of it being banned or limited, nothing changes in the youth (et al.) -- that would be my prediction.

I think there are deeper long term trends causing psychological problems in the west: move away from physical to cognitive labour; increasing community isolation and lack of social institutions; various failures of the state; lack of meaningful wage growth in key brackets, and failure of the "aspiration engine" to create opportunities; lack of time for parenting, moving to dual working-parent households; helicopter parenting caused by breakdown of social trust; lack of infrastructure and provision of environments where children can be known safe in public. etc. etc.

The major forces here are: move to a services economy; dual parent working households; lack of social services in state provision; state infrastructure moving away from providing for the young to paying for the old. This means much of how children grow up in the world is unphysical, disconnected, time-poor, risk adverse, overly demanding, etc.

All these tools to build something, but nothing to build. I feel like I am part of a Pyramid Scheme where every product is about building something else, but nothing reaches the end user.

Note: nothing against fluid.sh, I am struggling to figure out something to build.

Eh, it's not a plan, it's make believe.

It's a flimsy back-filled rationale thrown on top the mercurial (and often sadistic) whims of an American Caligula, so the elite enablers can pretend there's something rational - or even good - about the chaos and destruction they are supporting.

There isn't. It's just chaos and destruction.

I feel like there's some credibility to 'this time it's different'

The US economy depends on the country's position of world hegemon - the US dollar is the world's main reserve currency, the US enforces international order and trade rules via its military strength, it dominates technology and culture through 'US defaultism'.

I dont think AI even factors in to this.

The US economy is priced for global reach - if it manages to lose that through a combination of credible competitors, and loss of goodwill - it's going to be in heaps of trouble.

The looming US debt is also a great question - a lot of economists have argued that since most US debt is good. It's mostly in forms of treasuries purchased in USD that pay in USD - this means the indebtedness creates a huge amount of dollars abroad that foreigners have to then spend on US services, driving demand.

Should the US become an unfriendly power to the rest of the western world, it will find the demand for its currency plummeting, which I don't want to outline is a big issue.

All said, I think if the US continues down the political path it currently seems to be pursuing, 'this time it's different' actually will be.