quibono

I don't like the op-ed but I would agree with the main point or what I understand as the main point, even if the argumentation is weak).

It takes a mix of willpower / routine / systems / laws to keep people in check, otherwise we predictably go back to the path of least resistance.

On the ego-effect, I sometimes feel like cataloguing some PR-review quirks that are mostly caused by humans being humans:

1. Smaller PRs (that can be easily read) tend to receive more comments and nitpicks than a large change since it's easier for us to have all the PR context in our heads at the same time.

2. Most people are ego-tied to their code even if they pretend that they are impartial

3. Social dynamics around merging and reviewing code between senior/junior and older/newer employees

4. probably many more

I have been thinking about this for a while. I'm not a Luddite, I can see the amazing value that modern AI brings, and how useful it can be.

At the same time I can't help but wonder that this is almost too much for us to cope, the LLMs are _too_ easy to use. I think we're very good at pretending there isn't a problem here but there is definitely going to be some cognitive decline happening.

We want to pretend like reading over the output of an LLM is nearly the same as us making those changes ourselves but I think there's a lot of value in those boring and manual steps. And most people (including me) will be too lazy to not eventually offload most things to the LLMs.

In a way this is similar to how watching a lecture tends to give one an "impression" of understanding that doesn't correlate with reality. We need hands-on work and some course work to get our monkey brains engaged.

I can only imagine what effects this is going to have in education.

It depends on how you want to play or share the media.

E.g. I remember having lots of issues sharing smaller video files encoded with H.265 via both WhatsApp and Messenger. iMessage doesn't support H.265 (or at least it didn't work for me at the time).

My ignorance laid bare

How can one access Carbon? I only see Argon via gemini.google.com

Is this API-only or US-only for now?

Yes, after all there is no distinction between data and code since they're the same thing when it comes down to the bytes in memory.

It's used for any immuno related disease, it's crazy how many things it's used for.

Psoriasis, eczema and psoriatic arthritis being three that maybe you wouldn't think of when someone brings up methotrexate.

Not quite HOMAM2 but.

I have such fond memories of HOMAM3 and playing it in hot seat mode as a kid.

Interestingly the game is still massively popular in ex-Warsaw Pact countries. Although I think it’s having a resurgence in the US too.

For HOMAM3 there’s also the amazing HotA: https://h3hota.com/en/documentation

1. Read the post

2. Click on the hamburger menu in the top right

3. ???

Maybe a bit unorthodox but I have it plant 1-3 bugs into the code it writes (depending on the size of the MR I'm working on); they range from simple one-off issues to something more structural.

It then gives me a hint on the area or a typical code flow that would hit the bug - whichever gives me less info. I can obviously ask for more hints as I read along.

Obviously all honour-code based since I could just ask it to fix the bugs itself. I think this is something that can't be fixed systemically - either you're going to bother reading and thinking through the code or not.

Other than that I guess reading the tests - to make sure they fail without the code / fix, to make sure the setup makes sense etc.

Others mentioned this already but the pricing is steep. And to add a Dropbox-style comment, I think a big part of this can be handled via Coolify?

Is this sarcasm or are you one of _those_ Apple fans willing to rationalise every single issue their products have?

Thanks, this is useful. I think something like org-roam-dailies would suit me!

It seems Google is going for the integrability of AI into every single product they have over being an OpenAI/Anthropic style provider. Which is a shame because Gemini was great for a while, NotebookLM is lovely and the flash lite model was really good at structured workflows. So I’d love to see them continue the line.

No idea what gating Argon like that does for them.

I’m using both Obsidian and Emacs and yet my biggest issue is actually… knowing what to note down and when. I don’t know if others have a system for this. I also don’t want to end up with some over-the-top note-everything system - then again surely there is some middle ground here.

What kind of models can you practically run with ds4 on a 64GB M5 Max?

I’ve seen this a few times now, and Claude does not listen to this in the long term. It’s still terribly obnoxious.

I tend to run the content through something like Luna to deslopify now.

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.

Similar to vomit[0] and claudish-to-english[1].

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.

[0] https://github.com/zachahn/vomit/tree/main

[1] https://github.com/gvzdv/claudish-to-english

I love the information density on that page. Feels like very fresh compared to today's minimal pages.

Could you provide more detail please? Sounds interesting.

Is this a hardcoded limit or something relative to the input prompt etc.?

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.

100% agree, the fixup macro is amazing. It even fails gracefully when unable to commit for whatever reason.

The split one would be handy though.

Yes, good point!

I guess what I meant was: the only way for art to meet one of the ZKP criteria is for us to assume it's art.

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?

> scary rebase -i commands that can leave your tree in a half-broken state if you so much as sneeze

I'm glad to hear it, I thought that was just me. It gets especially hairy when moving commits around...

Plus I have 3-way diffs enabled and I usually get confused by which section is which at least once a day.

Also: does anyone know if `magit` has history support?