AI is nowhere near being able to produce a novel worth reading. The author's already heavily qualifying these ~10 page short stories, because the ratio of slop to moderately interesting content is still so unacceptably high.

Consider putting some energy towards finding more human sci-fi worth reading, because Asimov might be a pioneer, but he is hardly the most accessible or enjoyable read. I guarantee this brand of chocolate is better.

    I’ve been a long time vim user, and I honestly never really bought into the efficiency claims. That gets repeated over and over, but If you’re a slow typer then no editor can really make much of a difference.

    Little by little your movements become more complex and efficient, and the journey to figuring that out is fun and interesting.

    It’s just fun, and I don’t think that gets talked about enough

vi definitely doesn't scratch that "itch" for everyone in the same way. But for me, it's as though I found a cheat code. Getting better at vi feels like getting better at a game - only practicing this game makes you better at any number of tasks that are relevant to your daily work.

(although if you also want to get better at typing speed, there are surprisingly fun roguelikes on Steam for just this purpose)

The checks are a filter so they can apply manual review only to those plugins which pass the baseline (and automatable) requirements.

You are confusing code with application code. The latter thing you describe is a test, which is expressible in code.

    The valuable engineer is the one who sees the hidden constraint before it causes an outage. The one who notices that the team is solving the wrong problem. The one who reduces a vague debate into crisp tradeoffs. The one who identifies the missing abstraction. The one who can debug reality, not just read code. The one who can create clarity where everyone else sees noise.

    "The software engineers who will be most valuable in the future are not the ones who do everything themselves. They are the ones who refuse to spend time on work that A.I. can do for them, while still understanding everything that is done on their behalf."

    "The danger is not that A.I. will make people lazy in some vague moral sense. It is that it makes it easy to simulate competence without building competence."

    "In that world, the engineer is not replaced by A.I. The engineer becomes more leveraged because they are operating above the level of raw output."

    "The ability to explain why something works, not just that it appears to work."

    "That process is not optional. It is how engineers acquire and elevate their competency."

    "The support system may make you look functional, but it does not make you capable."

    "The challenge is not merely adopting A.I. tools. It is protecting the conditions under which real thinking, learning, and craftsmanship continue to thrive."

    "They will need interview loops that test reasoning, not just polished answers."

    "The organizations that handle this well will not be the ones that simply push A.I. adoption hardest. They will be the ones that learn to separate leverage from dependency, acceleration from imitation, and genuine capability from convincing output."

It would be more accurate if for the entire journey, the scooter driver also extolled the virtues of slow, luxurious, human-powered travel.

    This is not only average. This is actual magic.

    So let's be real: the SQL is average. The joins are average. The chart is average. And that took us less than 5 minutes and that was amazing, that is the entire point.

    You did not need a data engineer to model your HubSpot data, or a meeting to agree on whether it should be last-click or first-click or linear or time-decay or whatever.

    You needed a query, written fast, on data you already own. Your LLM wrote it. You confirmed it made sense. Your manager got a link.


    Honestly, average is clearly magic; prove me wrong.

It is like nails on a chalkboard.

    At that point, asking the model to e.g. note any ambiguities about the task at hand is exactly equivalent to asking it to evaluate any input

Prompt P at state S leads to a new state SP'. The "common jumping off point" you describe is effectively useless, because we instantly diverge from it by using different prompts.

And even if it weren't useless for that reason, LLMs don't "query" their "state" in the way that humans reflect on their state of mind.

The idea that hallucinations are somehow less likely because you're asking meta-questions about LLM output is completely without basis

https://aphyr.com/posts/411-the-future-of-everything-is-lies...