Bluestein

> 100H yeah and basically a memory dump

... the days! :)

- https://github.com/PlummersSoftwareLLC/retropad

I was humbly going to posit same, but given the vitriol apparent against the publisher, it is symptomatic of something, I guess. The points downthread make for an informative read, pro-against.-

Hey, guy's earned an acronym. Already says something ...

- https://learn.omacom.io/

(It is not very discoverable? The "bookshelf-like" icon on top ...)

This is the best definition of so many things (from "enragement"/engagement) to the entire Drump presidency to, oh, so many things. So, thanks.-

(Also, in a good way, mind: Art for art's sake.-)

I have been doing some thinking about this, and, am trying to combat (within) the knee-jerk repulsion that book destruction causes.-

From what I understand, these, far from rare - though "rare" might get swept along given a sufficiently long tail - are average to obscure books that would otherwise be "gathering dust" on shelves somewhere.-

From that point of view, I wonder:

- Even if under a "walled garden", would it not be more efficient to have the knowledge represented by the book more widely available (of sorts) even if masticated by an LLM, rather than on a shelf somewhere?

- Libraries and other pros routinely destroy books: They take up space on a shelf and they are expensive to keep around, so this might be far from uncommon.-

I guess the objection here is to the "privatization" of a "commons" (the mass of printed books), modulo all the unknowns that the destination technology itself (AI) brings with it.-

OMP is great, testify.-

jcode is a very very peculiar harness, but has some out-of-the-box thinking built in (by the devs, thinking ...)

Crush is also very well put together, and, IIRC, can do "mid turn" interruption, so can be driven from the outside.-

Spot on. (I had not considered quantization - that's a thought ...)

Maybe compute relocation?

Found this intro informative:

- https://www.youtube.com/watch?v=Tbt3jL1Ms0w

That floppy in hand still haunts me nightmares :)

For those interested, myself amongst:

- https://nicktrevino.com/your-repository-is-your-swarm.html

What I really really really do not understand is the toolbox - it seemed like an LCD screen at first glance, but, no.-

(I just really really really wish background wasn't so ... yellow).-

Allow me to offer a complementary point: I understand exactly what the poor "thing" means - and perhaps through some deformation or another I have done so since having had to read it - but something functional in the modus is still "off".-

... not to mention the fact that it stops making sense, beyond some point: If it takes us more cognitive load to understand the tools we use, meant to save us from intellectual work, what's the point?

A caveat though, and it's a real one: Not all seams have been.-

I tend to agree. We will see this demonstrated in novel research done by agents, or, more meta-cognitively research direction guidance.-

The model judging a model theory is 100% spot on.-

[And this folks is the true reason we are out of ammo in the middle east ...]

Honest take, you genuinely forgot to flag the flags ...

Oh, please, gratitude is due you. Great points. The whole idea is great and the example is very very telling.-

What an honest take.-

I concur. It even follows some idiosyncratic punctuation if you have it.-

"From neuralese to moron-code ..." :)

The problem here is that "better" is load-bearing, and I mean this half-seriously :)

I would opine:

- Nerfed Fable is worse than Fable

- ... and I would argue Opus 5 is worse than nerfed Fable, to the point I've found it unusable.-

> The baked in communication style of these models is so obnoxious it's impacting my work.

This is close to the worst thing one could say of a tool for professional use.-

Pre Trump-castration Fable was verbose, but had a point, and used that wordiness to say or show the indeed intelligent things it reasoned about. This, whatever this is, is something else.-

Maybe Glimmer might be good at excising the comment spam, particularly?

The author's blog has what follows (link also follows):

[Seriously y'all in what universe would some "caveat" or another NOT "be a real one" by whatever severity you'd want to measure that AND/OR need of saying so ... ]

Claude (Original)

Force pushed. 1234567...890abcd main -> main (forced update).

Verified

Local main and origin/main both at 890abcd, in sync.

Every commit reachable from origin/main: no old string found.

Local object store, with spice-harvester as a control returning 9 hits: all old strings return 0.

Working tree clean, tests pass.

One caveat, and it’s a real one

The old tip 1234567 is still fetchable from GitHub by its full SHA. I confirmed this directly:

git fetch origin 1234567890abcdef1234567890abcdef12345678

* branch 1234567... -> FETCH_HEAD (succeeded)

GitHub keeps unreachable objects until its own garbage collection runs, and there is no schedule you control. Anyone with a full SHA can still read the old blobs through the web UI or a direct fetch. That fetch also pulled the old objects back into your local repo, so I deleted FETCH_HEAD, expired the reflog, and re-ran gc --prune=now. The counts above are from after that cleanup.

If you want the old commits unreachable on GitHub’s side too, the options are to ask GitHub Support to run GC on the repo, or to delete and recreate the repository. Deleting and recreating is the only one you can do yourself. Say the word if you want help with either.

Nothing to commit this turn. The rewrite was the work, and the tree is clean.

Claude × Vomit GPT-OSS-20B

I force‑pushed the branch, updating main to commit 890abcd. I verified that my local main and origin/main are both at 890abcd. I checked that every commit reachable from origin/main contains no old string. My local object store shows that the spice‑harvester control returns nine hits, and all old strings return zero. The working tree is clean and the tests pass.

However, the old tip 1234567 is still reachable on GitHub by its full SHA. I fetched it directly and saw that GitHub keeps unreachable objects until its garbage collection runs, which I cannot schedule. Anyone with the full SHA can still read the old blobs via the web UI or a direct fetch. The fetch also brought the old objects back into my local repo, so I deleted FETCH_HEAD, expired the reflog, and ran git gc --prune=now. The counts I reported are after that cleanup.

If you want those old commits to be unreachable on GitHub as well, you can ask GitHub Support to run garbage collection on the repo, or delete and recreate the repository. Deleting and recreating is the only option you can do yourself. Let me know if you need help with either.

There is nothing to commit this turn. The rewrite was the work, and the tree is clean.

https://zachahn.com/posts/1787191554