mpalmer

15 saat öncediscuss

I don't disagree with any of the points in the post. They're even framed better than the average "I love using AI because X" post.

Unfortunately, you won't become a better writer letting AI do it for you.

mpalmer

evvelsi gündiscuss

The second thing is not an ad hominem, it's talking about what he did or how he did it, not who he is.

mpalmer

3 gün öncediscuss

Marketing departments everywhere have been letting internal corpspeak just leak out lately. OAI's announcement shutting down Sora was similar:

> To everyone who created with Sora, shared it, and built community around it: thank you

"built community"?

mpalmer

4 gün öncediscuss

Low-effort, low-quality self-promoting slop, of the sort where you assume that significant errors are present, so obviously generated (and unedited!) is the text, but it's hardly worth your time to actually chase them down.

mpalmer

8 gün öncediscuss

What, you don't like your caveats to be honest?

mpalmer

12 gün öncediscuss

Freedom of expression is inseparable from the right to privacy.

Should journalists be forced to reveal their sources if the subject of a claim sues for defamation?

mpalmer

16 gün öncediscuss

How exactly do you suggest blocking ads that appear inline in your LLM chats

mpalmer

16 gün öncediscuss

These are solid conclusions/lessons to take away for people working in creative disciplines. Enforcing constraints on yourself can be rewarding and productive (the 3% rule), and forcing yourself to pay attention to other people's work is challenging but invaluable. Even less than stellar work has things to teach.

And can I just say, thank you for writing something you can read in five minutes. Incredibly grateful for someone who respects the reader by not dropping 3,000 words on them - easy though it may be.

mpalmer

18 gün öncediscuss

    With AI, I can finally build what I've been dreaming about.

What was your dream before AI, exactly? Not to build a VCS for agents, presumably. But the entire value prop here is centered around agents.

This is not the first "agentic VCS" project which claims both N% VCS token savings, and "faster VCS operations". But how are either of these two things a bottleneck? No case is made for this.

    It dramatically improves the speed and context your agents need when working on serious projects: 50% fewer VCS-related tokens and 90% faster per operation.

So less context is an improvement? How much is 50% in practice? And how do my agents "need" a 90% speed increase (source, btw?) in VCS operations? What % of wall-clock time is spent in VCS commands vs actual inference?

"Agents locally and in the cloud no longer need a full copy of a repo to get working" - but was that ever a problem? And git supports shallow clones anyway.

    work on many tasks in parallel without needing to download everything or fight worktrees

Who is "fighting worktrees"? If you're concerned about all these downloads, why not use worktrees over a network share, as mentioned in the git manual?

mpalmer

21 gün öncediscuss

It's a useful term but humorously risks becoming auto-exemplary.

mpalmer

22 gün öncediscuss

All the benefits you're describing apply to the present moment; people with knowledge, self-discipline and expertise can leverage LLMs to great effect.

How many people like this will exist in a decade? Two?

mpalmer

22 gün öncediscuss

How do you measure the bundle of "skills" that comprises critical thinking? And if that's your analogy's distance running, what's the "riding a bike" analogue?

mpalmer

23 gün öncediscuss

I'm genuinely trying to cut down on complaining about slop writing, but how are you going to say:

    Ask yourself where you’re using technology to replace human moments rather than amplify them

...right after you've subjected me to four thousand(!) words of preachy BS about connecting with humans instead of taking shortcuts?

Let me say it again because I'm really getting sick of recent blog word count inflation: if you publish four thousand words on some topic, you better be an expert, a strong writer, whatever. Find a better reason than SEO to go over 1500 words.

mpalmer

23 gün öncediscuss

Well, sometimes there's flat-out nonsense that seems to have been written purely to back into the author's thesis:

    You cannot design an algorithm that eavesdrops on dinner conversation and dispatches someone to buy a street hot dog, because the person on the receiving end would immediately sense the machinery of it.

But usually there's also:

- Word count hovering between four and five thousand words - Dramatic/narrative section titles - "No X, no Y. Just Z"

Last but certainly not least, there's the Lists of Exactly Three Things. I counted literally thirty in this piece. Examples:

    - "...the ritual of a human voice, the small exchange about an anniversary or a first date, the warmth of being recognised."
    - "Who was celebrating a birthday? Who was on a first date? What had a regular not finished on their plate six months ago?"
    - "You can’t purchase it, automate it, or accelerate it with a clever marketing campaign."
    - "...forgive outages, laugh off a late delivery, stay through a price increase."
    - "...the food arrives hot, the bill is accurate, the room is clean."
    - "You notice, you adjust, you respond."

mpalmer

24 gün öncediscuss

Good luck with your trade secrets I guess

mpalmer

24 gün öncediscuss

Unless we're doing away with human accountability, the responsibility to accuracy (and whatever other statutory requirements) will remain the same, it will just be concentrated among significantly fewer federal employees.

mpalmer

26 gün öncediscuss

In the spirit of the project, I can replace this with a "one-liner":

    Is there a simpler solution?

mpalmer

27 gün öncediscuss

Cheers. Absent explanation, I do think it's reasonable to assume that you stood by the wording/claims of the README when you posted it, but I appreciate the patch you made to the docs.

FWIW, re: best practices, your install script potentially runs `rm -rf` on the user's global skills whose names shadow your project's.

mpalmer

28 gün öncediscuss

[dead]

mpalmer

28 gün öncediscuss

Reduce Fable tokens by 80%, simply by not using it!

> I am fairly convinced this is the shape serious agent work keeps converging toward.

"this" being "plan with expensive model, implement with cheap model".

Anyone who follows HN would be hard-pressed to disagree; this architecture is re-invented twice monthly.

https://www.facebook.com/groups/vibecodinglife/posts/1946207... https://github.com/openai/codex/discussions/10628 https://build5nines.com/stop-burning-premium-requests-how-to...

> Not because it is aesthetically pleasing. Because every other shape eventually runs into the same boring failures: context rot, self-grading, goalpost drift, and merge chaos.

Actual failure isn't boring. But struggling through a generated software project that celebrates its own genius and doesn't have a single self-critical or genuinely reflective thing to say...at least watching paint dry I might get giddy off the fumes.

I'm not interested in critiquing the project itself, either, you'll just run that through a model, too.

Submissions

Ask HN: Should the term "cognitive surrender" apply to writers who publish slop?

comments