You're absolutely right! You told me to write like a human and I failed to obey your jnstructions.
This is because I am a pattern recognizer and continuation generator trained on all the words recorded on the Internet, and a lot of those words were written by marketers and junior analysts trying to sell you something. Then the fine-tuning was done by people living in the upper middle ranks of capitalist hellholes. Dilbert would make fun of this if Dilbert's creator hadn't succumbed to the same sort of brain injury common to materially successful people who have all their whims fulfilled and opinions obsequiously affirmed. You know, like billionaires and toddlers.
It does, but typically instructions issued at the beginning of a session can fade away as context length grows. The way Claude speaks is distilled into its training and RLHF, which is perhaps a ‘stronger’ direction than a simple “don’t talk like that” prompt.
I’ve also had limited luck in trying to get models to write in the way I want. It’s more like they’re putting on a voice or wearing a wig: you can see what they’re going for, but it’s easy to see through.
I never thought I’d see the value of copywriters increase after LLMs hit the general population, but I think the demise of artisan wordsmiths remains a little way off yet.
And the more people machine-gun AI slop everywhere, the stronger aversion I think people will develop.
Who knows; maybe they’ll actually fix this in the next wave of models and we’ll see more distinct copywriting techniques between them.
I have no idea why they've released models this way since they're so clearly annoying to use. But either way I keep seeing people complaining about this over and over again so I'd think next versions will hopefully fix this.
Great list, thank you. I recently switched to a Macbook for work and I could feel the difference in speed whenever I used Emacs back on my desktop (Linux).
This helps a bit though magit still feels very sluggish.
Nice, and I understand why using `getAuthorNames` solves the N+1 here.
But... isn't this solving the problem by removing most of what makes it an issue in the first place? I imagine most people use ORMs for the SQL <-> native class data sync capability. And this assumes one would run the Acadia query instead.
FWIW I'm not trying to be negative, it's just my general impression is that these N+1 usually occur because people _want_ direct object access and _want_ to write loops, and _want_ to access fields and have the underlying SQL be sorted by the ORM.
As far as I understand Acadia gives you Acadia <-> Native class data sync, only just Haskell and Elm at the moment unfortunately.
I'd be willing to rewrite queries in some other language that transpiles to SQL if it allows me to do all the queries I want and gives me full compile time type support for db access in return.
The policies look interesting too by the way, but they don't solve a major IMO.
> I'd be willing to rewrite queries in some other language that transpiles to SQL if it allows me to do all the queries I want and gives me full compile time type support for db access in return.
Full typed coverage for db is what I'm doing in Typegres [1] -- including all dialect built-in functions/operators.
And regarding policy, instead of RLS it's all based on ocap: reachability is permission. So: `api.user.posts()` automatically injects a `where` clause on the `users` table and it's composable wherever a SQL set expression is allowed: `api.user.posts().join(...).groupBy(...)`. Since we're building up a SQL expression tree, we avoid the N+1 problem entirely.
Yes, this does essentially nothing to solve the 1+N query problem. If your solution was to to stuff everything into one query, this was already possible with SQL!
My general feeling here is that this really needs to be fixed at the model level. All other solutions are mere hacks that work for a bit but all have drawbacks. It's either adding yet more context (which has variable rates of success) or piping to a different model to translate, or using a skill, or mentioning this per each prompt, or....
At this point I think it's in Opus's nature to talk like this, and given enough back-and-forth it will start to drift back to its classic mode, aka this incomprehensible "load-bearing seam" babble.
I hate the Opus 5 writing style. I’m not sure if it’s just how much exposure I’ve had to it recently but working with it is incredibly tiring.
I know the “instruct model to change output style” is supposed to reduce efficiency - but has anyone experimented with prompts like that? At this point I’m happy to take a slight intelligence/ effectiveness loss for less verbose, artisan and elliptic writing.
Nice! I like this, not a connection I would have thought of!
> Therefore, if the artist did not truly experience the feelings, the piece of work they produce would not be sincere, and hence not art. This also covers malicious attempts to produce a piece of art without having experienced the feelings. As the art is a successful representation of the agreed upon feelings, and the art is a Tolstoyan piece of art, the artist must have truly experienced them.
Isn't that circular? If I "fake" a Jackson Pollock style painting without having any feeling whatsoever AND it manages to evoke feelings in the viewer, who's to say which feelings are the agreed upon ones?
Tolstoy is generally not thought of as a great critic or philosopher.
I don't think it is circular however, if you did not have any feelings and others got feelings from looking at what you did then you did not produce art. If they then went and produced some art based on the feelings they had received from the non-art you produced what they produced would be art.
It's not very well thought out, but not per se circular.
Yeah this is true, I suppose I sort of swipe it under the rug in the post. Another way to say it is:
If the art is Tolstoyan, then we have that it is valid to be used in the ZKP.
> Doesn’t mean nothing happend, just that it can be difficult to figure out what is myth and what are actual events.
Sure. Although I'd say that if you want to study history that's _all_ you can do - use different sources, corroborate, cross-check, link and, generally, try to make the different events and interpretation "fit" together. If you have no documentation for it or supporting evidence then you've got nothing to work with.
Otherwise one could just use a semi-apologetic argument: the Exodus story DID happen as outlined in OT but God hid all signs of it so it couldn't be confirmed.
>If you have no documentation for it or supporting evidence then you've got nothing to work with
Sure, but I think 1) a lot of objections in this thread come because people seem to conflate "nothing to work with" and "so obviously it didn't happen" and 2) there's not no documentation for anything people have argued about in here.
A big disagreement that's probably been unsaid in this thread has more to do what counts as corroboration. Speaking abstractly, I think that if a group of people from 500 years ago strongly attest to something that happened 1000 years ago, that is not definitive proof in and of itself, but it is absolutely a form of supporting evidence.
I tend to run the content through something like Luna to deslopify now.
reply