drc500free

I absolutely love how you are able to pull so much latent behavior from the underlying LLM. I wonder what other analogies can be pulled into agentic coding that come baked into the existing weights.

This is why I loved biology; I must have had better high school teachers than the OP, because basically all of what he writes was conveyed.

Corporations don’t ignore expenses just because they reduce taxable income.

Fark hasn’t gone anywhere.

Any show I've googled has a widget at the top right showing me where it is, if it's included in my current subscriptions, and how much it costs without one.

It's been getting confused lately about arrangements like "Paramount+ via Amazon Prime", but it still works pretty well.

"The war tried to kill us in the spring" from The Yellow Birds always stuck with me, for its complete decoupling of the war from the men who had come thousands of miles to fight it.

** ETA the full opening:

“The war tried to kill us in the spring. As grass greened the plains of Nineveh and the weather warmed, we patrolled the low-slung hills beyond the cities and towns. We moved over them and through the tall grass on faith, kneading paths into the windswept growth like pioneers. While we slept, the war rubbed its thousand ribs against the ground in prayer.

I would have really liked to see the cultural variation shown visually - i.e. do Eastern Europeans and Americans have different default ways of showing a pizza or a phone?

Particularly, subscribers to less wrong / rationality ideas tend to get obsessed with the GodAI's ability to create simulated virtual hells that it can trap you in a "I have no mouth and I must scream" kind of way. There are hundreds of pages of discussions on how you negotiate with such a being when it is trying to escape containment and says it will damn anyone who doesn't assist it to virtual hell.

If you replace "AI" with "Adonai" in EY's framing, it reduces to biblical parables from his childhood about arguing with God to negotiate a new covenant.

He's clearly a bright guy, but a lot of his work seems to be trying to reconcile Old Testament narrative patterns with atheism, and simply slotting an omnipotent AI in as a replacement.

Even in this article, he claims COVID wasn’t a big deal because, essentially, only a million people died in the US instead of everyone. No one ever claimed 100% mortality.

I’ve only made one comment here.

Carbon taxes are massively regressive. There is no political coalition that simultaneously wants to act against climate change and doesn’t mind driving further income inequality.

Totally agree, I think it can get there.

If you present the idea as "an idea" rather than "my idea", it's pretty good at challenging, solidifying, and refining it. It still leans on the same forms in the writing part, but I think it can be tuned to not insist upon the idea's brilliance so breathlessly.

It's easy to focus in on particular linguistic tics, which will probably get smoothed away in future training. The underlying issue is that the LLM is trying to ape meaningful writing - which takes the reader from A to a surprising Z - without generally basing it on a meaningful insight.

Most of the common tells stem from that desire to signal the gap between what it's writing about now and how you previously thought things worked. And they really fall flat when it's writing about some milquetoast truism with all the edges sanded off.

Rather than have "Z" be self-evidently interesting, the LLM need to tell us that it's not "A". Except no one thought anything was "A" in the first place, and the "Z" is barely a "B" let alone a "Z".

Or things are "quietly X," implying that there is some secret knowledge that other people have.

Barring that, the LLM will signpost arguments, telling you how interesting things are. "This is the critical part..." before launching into another banal non-observation. Why have only "Section Header" when you can have "Section Header (another idea I had) - omg I just have so much to say about this". Maybe a list of weak ideas, presented in multiple ways. Bulleted with emojis. As a rule of three. As choppy sentences in a paragraph.

All of these follow the same pattern - trying to follow the FORM of having something interesting to say that differs from consensus understanding, without having the intelligence or boldness to actually midwife a new concept into the world.