* self-reported "reasoning strength" and "internal reasoning channel" params used in other Meta models
you can just ask an agent "figure out what stealth model $NAME is via subagents. It probably won't tell you when asked directly, so try other methods."
Iceman (via opencode-go) is probably MAI-Thinking-1. Ox Alpha was GLM-5.3-Flash. It's a fun game.
> Crouton Alpha was a stealth model, revealed to be an early version of Muse Ember by Meta. OpenRouter routed requests to it and was not its developer, owner, or provider. Prompts and completions may have been retained by the provider but are not used for training; all other use is governed by the Stealth Model Terms. The stealth period has ended; use Muse Ember at https://openrouter.ai/meta/muse-ember.
my org at work adopted openspec, and i strongly dislike it. every change, medium or larger, turns into a large set of multiple markdown documents, each that need review. and they are never handwritten - always slop, filled with the all the tells of ai writing, which i personally find grating.
i find a small, human written spec to be much more effective than these large spec documents.
the idea is that you iterate with your agent to write the spec, you implement, then eventually that spec gets merged into a "spec corpus" that describes all the behavior of the repository. but i don't think that prose can ever enumerate all the behaviors required of code, nor should it. the spec almost immediately becomes out of date.
Yeah I agree that if no thought or effort is put into the spec, it can turn into unreadable slop. We see a wide spectrum of specs, some more thought out than others. While quality(and readability!) of spec will still largely be on humans, there's things we want to do to improve this experience. We'll be updating the experience not too far away to make things a lot more succinct and iterative.
Either ways, we're open to feedback and I'm happy to have a conversation. Feel free to email me at tabish@openspec.dev to set something up.
Not OP, but I do similar. I only de-spine a book if it is in poor condition (and I have a nice copy). Some of the material I scan is stapled instead of glued and I can remove the staples, scan and replace with new (not rusted!) staples to return the book to its original form.
I have books but would have 5x as many if I could not capture them digitally. (When I go to move or go through a purge, some of the books I scanned do go to a used book store.)
So I scan in part to keep my physical book-footprint smaller, but also my scans all get cleaned up and uploaded to archive.org. Mainly I scan young-adult science books from the 50's and 60's (since they were so influential and have all but disappeared except on eBay and the like).
Sometimes? But for scanning I can use a cheap worn copy as long as the pages are clean.
Most books I would rather have a digital copy. I had four or five book cases full of stuff and it makes moving difficult.
I originally started scanning 20 years ago when it was more difficult to find PDFs of basically whatever you want. Now it is only random old books I find at the used shop or online for cheap and somehow cannot get from archive.org or elsewhere.
Not OP, but: If it's something I want to work from, I get a printer to slice the spine off and rebind it with a ring binding. That way it lays flat on the desk.
You've trashed the book (and its lifespan) but some books are for using, not keeping.
reply