> Simply put, these companies have fallen for a confidence trick. They have built on centuries of received wisdom about the efficacy and reliability of computers, and have been drawn in by highly effective salespeople selling scarcely-believable technological wonders.
I see what you mean - it wasn't intended to be a parallel to mechanical calculators.
However, the title implies that they were a trick - otherwise why is the "confidence trick" 400 years old?
I feel like this kind of imprecise use of language is what makes it difficult to interact with LLMs in a meaningful way - perhaps that is the reason the author seems to dismiss the value of them.
Not related really, as you can (and should) publish BREAKING.md separately. Release notes should inform more about new stuff than the update process. Usually PRs have details, so release notes can be easily automated. Migrations, on the other hand…
+1 on separating "how to upgrade" due to breaking changes from "what’s new". A dedicated BREAKING.md / MIGRATIONS.md is a really good idea.
One thing I am trying to do is make the generator surface breaking/migration items explicitly, but I still think anything that requires human judgment (migration steps, caveats) should be hand-curated in a dedicated document like you suggested.
I do a lot of logical-clock based synchronization using asyncmachine.dev (also in Go), you may want to check it out as “human time” can be error prone and not “tight”. It does involve forming a network state machines, but connections can be partial and nested.
Your results are very hard to read due to formatting, but the idea is interesting.
You should always distribute AST-level refacs, which are deterministic, instead of prompts. You can easily prompt these out, but nothing really changes here besides who writes the migration (human vs LLM).
> all websites are using some kind of tracking to know what kind of users visit
Server side analytics exists, its the ad optimization and feeding data brokers which is the reason. You can disable cookies for google analytics (storage none).
> Simply put, these companies have fallen for a confidence trick. They have built on centuries of received wisdom about the efficacy and reliability of computers, and have been drawn in by highly effective salespeople selling scarcely-believable technological wonders.
Calculators are ok, but LLMs are not calculators.
reply