So sending your implementation team out is “not just smart — it’s required” (to use everyone’s current favourite phrasing).

It’s funny that this technology only admits in-band signaling. Given that, any foreign content is risky. It’s actually quite interesting that the current technological ecosystem is built around a high trust situation: npm, pip, cargo all run foreign code in the developer context and communities have norms of downloading random people’s modules.

And so I suppose it’s no surprise that we use LLMs - another tech that is high-trust: since it has no out of band signaling ability.

But it seems like we’re very close to the end of the era where someone will use (in a sensitive system) arbitrary web content carrying the equivalent of merged code/data.

Undoubtedly these various hosts will come under pressure from spammers and the like and they will react by placing extraordinary barriers around accessing the code.

That’s fine but it reminds me of the later stages of online forums, where it was impossible to browse most threads because you had to create an account and then build up community points until the screenshot of the kernel panic on the ZTE phone would be visible so you could see if it’s the same problem as yours.

GitHub was big and powerful enough to not need all of this but now we’re going back to the era of decentralization and I suppose with that come the pros and cons.

Spent last evening so frustrated I also got ChatGPT subscription. Makes me wonder if I should be using Gemini on pay per use with custom harness.

With my own harness performance is way better but cost goes up because no subscription.