> It didn't work, and why it didn't work turned out to be more interesting than the policy would have been.

Spoken like a true Claude.

Snarking aside, I am glad that our AI agents make it cheap enough to do these experiments and publish these write-ups that people finally bother to publish null findings. Very useful!

▲

lukeschlather an hour ago | parent | next [-]

The idea of publishing null findings is very attractive, but the problem here is that they didn't record what the actual problem they're trying to solve is. It seems a bit like someone prompted Claude to try and make tool calls more efficient and Claude responded with a detailed writeup on why LRU can't be beat for making a KV cache. Which might be interesting, if that were the question I had asked.

▲

phoghed 10 hours ago | parent | prev [-]

That line doesn’t strike me as overtly AI written, overall yes though

▲

cryptonector 4 minutes ago | parent | next [-]

The whole thing is clearly written by Claude.

▲

wgjordan 9 hours ago | parent | prev | next [-]

It's using a couple textbook [1] LLM tropes, 'negative parallelism' with a 'here's the kicker' tone.

[1] https://gist.github.com/ossa-ma/f3baa9d25154c33095e22272c631...

▲

isolatedsystem 8 hours ago | parent | next [-]

I always have a tinge of...perhaps 'sadness' when reading such articles because they are a lot like those large fishing nets that drag along the bottom of the ocean catching and destroying in quantities unneeded. From this list:

- Quietly/Delve/Tapestry/Landscape: they're all lovely words. I love(d) using them.

- "Serves as": I use this all the time too.

- "The result? Devastating". Perhaps it is a bit stilted, but "Outcome? Predictable." could be a nice turn of phrase.

- "It's worth noting": All academics everywhere use this in papers. See also: "Notably", "Essentially", "In general" and other such fillers that we reach for.

- "Think of it as": This is such a useful phrase to explain something. Analogy is how we learn after all.

- The fucking em dashes. I love them, and screw everyone who suggests one should stop using them. One big reason for using linux is the compose key, so the em dash is never far away.

- Same with the unicode decoration. Nah, screw you. I use these symbols all the time: °, ×, →, ⇒ etc. in my own notes. Again, compose key ftw.

Etc. (the list is endless)

I know what people will say, that everything is contextual, one has to study case-by-case etc. But I can't help feeling that someone is pointing a finger at me and accusing me before-the-fact. Just, AI has polluted the joy of writing.

▲

AnimalMuppet 8 hours ago | parent | prev [-]

I've seen Douglas Adams use almost exactly this in Dirk Gently's Holistic Detective Agency. A professor (IIRC) is talking to a former student. Quoting from memory

"Did you ever actually finish any papers?"

"No. But the reasons why not were always absolutely fascinating."

So, yeah, for me personally it's not an AI tell. I've seen it in the wild before AI.

▲

shakna an hour ago | parent | next [-]

In that quote, Adams doesn't repeat himself, before making an assertion. He realises the audience has more of a context window than three words.

The same is not true, of the token generation that... Mostly Claude models... Have taken to.

▲

jchw 8 hours ago | parent | prev | next [-]

Yeah, but that doesn't sound like AI at all. Not even close.

▲

dougabug 7 hours ago | parent | prev [-]

LLMs glom onto pre-existing tropes, idioms, and verbal constructs.

▲

MarkusQ 5 hours ago | parent [-]

And then subtly misuse them.

LLMs write like some people cook, adding bespoke artisanal Belgian sea salt, truffle oil and weirdly specific cheese without any thought given to how the result will taste.

▲

phoghed 4 hours ago | parent [-]

> And then subtly misuse them.

For example?

	▲	porridgeraisin 2 hours ago \| parent [-]
		https://x.com/badlogicgames/status/2098868942685012405

▲

jubilanti 9 hours ago | parent | prev | next [-]

But it is specifically one of Claude's ticks

▲

moomin 9 hours ago | parent [-]

It is. And the reason for that is* surprising: the base knowledge corpus is clickbait internet articles.

*not at all

▲

twoodfin 8 hours ago | parent | next [-]

I suspect it’s more like Claude etc. optimizing for a tone that gets the green checkmark from RLHF reviewers, probably over and over in many contexts where style is otherwise an incidental concern.

▲

philipallstar 8 hours ago | parent | prev [-]

It is more surprising than that: it's because the humans in the loop like it.

▲

vkou 5 hours ago | parent | next [-]

If you're being given an A-B choice between cinnamon-flavored shit and lutfisk-flavored shit, you might convince the experimenter that cinnamon-flavored shit ranks highly in user preferences.

	▲	lukeschlather an hour ago \| parent [-]
		I would expect a preference for lutefisk flavored shit, the problem is then you then deduce from that that people prefer lutefisk flavor over cinnamon, rather than that you should stop feeding people shit (and also stop feeding them lutefisk.)

▲

twoodfin 6 hours ago | parent | prev [-]

The LLMs are going to turn us into stochastic parrots.

▲

r_lee 10 hours ago | parent | prev | next [-]

I'm guessing he means overall the kind of circling and concluding that Claude does, like "the actual truth is more interesting than it seems" or "the real smoking gun is not the x, it's the y that was under our noses all this time" type of writing.

	▲	dgacmu 9 hours ago \| parent \| next [-]
		"That's not a result, that's a broken harness, and it's worth publishing because I expect it to be common." That's Claude. But I agree and am also glad the author, uh, clauded this up. :)
	▲	wongarsu 5 hours ago \| parent \| prev [-]
		[dead]

▲

rrobukef 5 hours ago | parent | prev | next [-]

While AI was clearly used to generate and structure a first draft, I say it has been extensively rewritten by the author. In my experience, AI tends to avoid the first person, instead writing from a passive observer or even using sentences without verbs. The length of the sentences is also more natural. AI had trouble with bind-words in an argument. It just states separate facts and assumes because they are stated in order you have a reasoning. I'm not seeing that here.

Of course, idioms are preserved, and not everything is rewritten.

I quite ok with this style, it isn't grating. I expect this will be a style we'll see more of in science.

▲

fluidcruft 8 hours ago | parent | prev [-]

This phrasing is a very specific "Hello, this is Claude"