closeparen

People conservative enough to drop the required nuclear bomb on the transit workers union to be able to deploy something like this won't pay for it, and vice versea.

>re-used

Perhaps even by other people, and over time, continuously improving as we discover new use cases or that things are more complicated than they seemed on the first pass. Like... regular software, and not "do[ing] it all in Claude or Gemini or ChatGPT"

A chat window that takes multiple seconds to respond and behaves non-determinstically is a pretty bad paradigm for most computer tasks. It just happens to work for software development in particular.

Twitter consensus now is more like LLMs will be entirely commoditized, apps & features will be cheap, and only systems of record will have lasting value.

Everyone is saying this about "the factory." I have seen some successful fix and migrate campaigns for well-defined, local transformations such as retroactive fixes for new lint rules, flaky tests, or library migrations. But so far the attempts to do nontrivial new functionality in this manner have made big messes that take more effort to review and correct than simply hand-feeding 1-3 vanilla Claude Code sessions with my full attention.

>Programming is something you can't get paid for.

That's the economy. It's not like all our problems are solved or everything that needs building is finished, even in very AI-forward tech companies. We are busier and working harder and longer hours than ever, and we've been hiring thousands of people in India.

True leading up to 2010. The couple of kids who had the original iPhone or the 3G were unusual. Most of my classmates - including myself - got one between the 4 (2010) and the 5S (2013).

The timeline is more plausible for the rise of short-form video.

Essentially every high schooler had an active Facebook account and essentially every school paper was written on a word processor by, like, 2010. By 2018 even Instagram is starting to be played out. I would be very surprised to see a material increase in the share of US or western students using social media over the 2018-2022 period.

People need to stop believing insane, delusional things like the existence of a human being with a certain name, address, phone number, birthday, SSN being secret or private information.

Downstream of that, people need to stop accepting knowledge of the basic public metadata fields or possession of images containing them as evidence of identity verification. Do actual public key cryptography on the internet or check biometrics and the document’s physical security measures in person.

The proposal I’m hearing is to make people training models accountable for anything users do with them.

Obviously you’re going to keep the model behind an API and be very selective about the people allowed to call and the queries it’s willing to answer, in that case. As Anthropic has done with Fable. But that is voluntary restraint - mostly in today’s regime we get frontier capabilities in open weight models on a ~year delay.

I do not buy that LLMs and the capability to run them are fundamentally different from other software or general purpose computing infrastructure in this regard. Moves to ban open source software or force OEMs to put little cops in everyone's computers are bad.

One through eight read as the list of sacrifices you make in having children. But the experiences of loving and being loved back seem at least incomplete without that.

Even startups that beat the incredibly long odds to become successful mostly aren’t successful enough to make up for a long stretch of not earning BigCo RSUs.