Well my coworkers and I realized that the opt out form just needed an address. We contemplated pulling all known addresses for the entire country and automating submitting them all over several months to opt everyone out. I don’t think it ever materialized but we had a good chuckle about the emergency meeting the Yellow Pages web devs would have had and at what percentage of opt outs.

2. Use certificates and your own CA.

3. Use the virtual serial console for first login.

4. Use cloudinit to add a custom software repo, then use that to install a custom package that does the initial work.

/users/ returns a 404 in an API means that this resource does not exist. As in, this is not a part of the API.

/users/123 returns a 404 means this user record does not exist.

Yes this means that a 404 is context dependent but in a way that makes it easier for a human to think of and reason about.

The harness is the part that makes the API calls, interacts with the user, makes the function calls, and keeps track of the conversation memory.

You can also use the LLM to summarize the conversation into a single shorter message so you get compaction. And instead of statically defining which functions are available to the LLM you can create an MCP server which allows the LLM to auto-discover functions it can call and what they do.

That’s the whole magic of something like Claude Code. The rest is details.

I recently did a lawn tractor conversion from gas to electric and what I got was in my opinion significantly better and more reliable than a commercial option at 20% of the price but it is limited to 4mph. Scaling it to 5 would require a lot of custom fabrication and a much more expensive drive motor. Once this tech is significantly better and cheaper to the point of being a commodity it will be a different story. For now it just isn’t.

Realistically the future of all this is that open models become good enough that LLM as a service becomes a commodity with a race to the bottom in terms of cost. Given where we are today I can easily see open weight models in 2-3 years making Anthropic and OpenAI irrelevant for everyday development work (I justify this like so: if my coding agent is 10x smarter than I am, how would I understand if it did all the right things? I want someone of roughly my intelligence for coding. I can see use cases for like independent pharma work or some such where supergenius level intelligence is justified, but for coding ability for mere mortals to reason about the code is probably more important).

And don’t get me started on memory management. Nobody even knows how to use malloc(), let alone brk()/mmap(). Everything is relying on automatic memory management.

I mean when was the last time you actually used your magnetized needle? I know I am pretty rusty with mine.

I was wondering when someone was going to point it out. I actually have only been using it since about 2009 after a brief flirtation with SVN and a horrible breakup with CVS.

Just like you don’t expect someone else’s local codebase to always be in a fully working state since they are actively working on it, why do you expect their working branch to be in a working state?