35 comments

  • rzk 21 hours ago ago

    An interesting solution suggested in the replies (https://x.com/andrew_n_carr/status/2081534245370314816):

        The fix for this is to say: only report to me in ASD-STE100 Simplified Technical English.
    
    More info about it here: Simplified Technical English - https://en.wikipedia.org/wiki/Simplified_Technical_English
    • mechanicum 18 hours ago ago

      I was curious so I asked Claude how it would do that: https://gist.github.com/waddie/b26166eec6cf675c044c09a95a754...

      I thought this bit was interesting:

      > TE has no register for hedging, ownership of an opinion, or acknowledging that a reasonable person would disagree. Modality is roughly can / must / do not. […] Where a thought can't be said in STE without becoming a lie, I'd mark it and say it plainly rather than mangle it. Confidence and disagreement are the two things I'd insist on smuggling through.

    • artogahr 18 hours ago ago

      I looked into it a bit more, and while it does look helpful in the first glance, it actually isn't a good fit for code. It's very aviation-terminology-focused.

      A better guide would be something like Google Developer Style Guide

      • quinncom 14 hours ago ago

        Or, as the Wikipedia Simplified Technical English Wikipedia mentions, use Plain English or Plain Language as non-aerospace alternatives:

        > The US government's Plain English lacks the strict vocabulary restrictions of the aerospace standard, but represents an attempt at a more general writing standard.

        https://en.wikipedia.org/wiki/Plain_English

        > Modern corporations and academic organizations hire technical writers already trained to follow a simplified form of English that the layman reader can easily understand, known as plain language (PL).

        https://en.wikipedia.org/wiki/Plain_language

        And so we've looped back around OP’s “plain English” phrasing.

    • dizhn 19 hours ago ago

      Nice. It sounds like doing a few passes on industrial product documentation with this might be beneficial.

  • usui 20 hours ago ago

    I've had to make the same request multiple times recently. Has anyone noticed it getting worse with the more recent models? It reminds me of when someone is trying to convince you of their intelligence by replacing simple and straightforward explanations with words pulled out of a thesaurus, so maybe that's the objective of these more recent iterations. Throwback to grade school.

  • rzk 21 hours ago ago

    Damn, I've been telling the same thing to Claude, good to know I'm not alone. I've also noticed that Opus 5 is much worse in this regard than Fable.

    It's as if the model is speaking Mentalese, or in some "bag of concepts" language.

  • chantepierre 21 hours ago ago

    I've had "tractable beachhead" a bit earlier today. Like in "the tractable beachhead was the coupling between X and Y".

    A bit of googling did not help me, I have no idea what this is even supposed to mean.

    • naruhodo 16 hours ago ago

      I wonder if this is a "loan idiom" from a non-English-speaking culture.

      > Det är ingen ko på isen – “There’s no cow on the ice” (Sweden)

      https://bigthink.com/high-culture/idioms-around-the-world/

    • sdwr 21 hours ago ago

      Tractable is solvable, the opposite of intractable, and a beachhead is a landing point for an invasion.

      A tractable beachhead is a solvable first chunk of work that sets you up for the rest of the project

      • euroderf 18 hours ago ago

        Wise man say: A journey of a thousand miles begins with a single tractable beachhead.

        • kridsdale1 15 hours ago ago

          It was true at Normandy, anyway.

      • chantepierre 20 hours ago ago

        Thanks. This is the first time I encounter the word "beachhead", and googling a bit made me indeed saw something related to an invasion. But I was so annoyed by the claudeisms that I closed the tab and just asked it to rephrase instead of trying to make another step towards its vocabulary.

      • ButlerianJihad 21 hours ago ago

        The art of rhetoric and human communication involves knowing your audience, and when using idioms and metaphors, you choose those which are shared in common to be immediately recognizable and impactful.

        When I was 19, I had a psychologist who employed a lot of baseball idioms. "We'll touch base next week..." and although I am not a baseball fan, my father is, and we're all Americans, and so the baseball references were well-understood by his audience of one.

        When an LLM starts going off about a "tractable beachhead" that behavior indicates that it's unaware of its audience, and also ignorant of how to put together a human idiom. That's exciting that emergent behavior is coining new idioms that may be applicable to some situation, and also explainable by dudes on Hacker News, but that wasn't the point of the comment.

        The point is that the LLM's audience wasn't a veteran of D-Day in WWII, and even with an understanding of what those words mean individually, neither he nor I recognized "tractable beachhead" as a meaningful idiom for speakers of standard English.

        • bennettnate5 20 hours ago ago

          > That's exciting that emergent behavior is coining new idioms that may be applicable to some situation

          I dunno, it feels pretty similar to an elementary student blindly swapping words with a thesaurus to increase the sophistication of their writing (which I readily admit I was guilty of doing once). It sounds more intelligent but lacks substance.

          • bluegain 18 hours ago ago

            FWIW as a humanities nerd, “tractable beachhead” packs a lot of nuanced meaning into two words. It’s probably not the right vocabulary choice for most audiences, but it isn’t empty or arbitrary.

            Tractable = you can make it work, but it’s not going to take care of itself, you have to get your hands around it

            Beachhead = you’re on a mission, you’re trying to probe to find the right way in to get started to eventually accomplish the whole thing, but first you have to find a little spot to get situated and then expand from there.

            • wzdd 17 hours ago ago

              It does, but in the same way that LLMs take two paragraphs to make a one-sentence point: by being weirdly specific and also redundant. LLMs don’t have a sense of whimsy in the face of RLHF, so if it’s proposing a solution, the solution is tractable. All implementation plans start with a beachhead.

              “A good starting point” is almost certainly all it needed to convey and what it should have written.

            • chantepierre 17 hours ago ago

              This kind of nuance is very suited to a mother tongue and I would probably like it in French, but as a non-native speaker who uses english mainly for professional or hobby stuff, claude-speak is becoming a bit off-putting.

              My only exposure to english literature comes from the Brontë sisters at this moment in time.

    • tengbretson 12 hours ago ago

      It's a shame that LLMs took off at the exact same time humanity entered it post-literate phase.

    • potsandpans 6 hours ago ago

      There's a scene in the movie Clifford, starring martin short. "I just need you to talk to me like a real human boy! You can't do it, can you???"

      "...the load bearing seam is the self referential spin. Superstition compounds throughout your entire pipeline."

  • mmarian 3 hours ago ago

    Good to know it's not just me! I also found it's way too verbose. So much so that I added an entry in my Claude.md telling it to be concise.

  • j-pb 18 hours ago ago

    Ah that's just because the new training set also includes "The King in Yellow".

    • btschaegg 15 hours ago ago

      Imagine someone sneaking in The King in Yellow into the training sets used by all projects training models somehow, breaking all future models irreparably -- and then the engineers trying to find this poison pill in the dataset and going mad one by one as they find it and aren't able avoid reading into act 2.

      …should make for an interesting SCP story :)

  • veganmosfet 20 hours ago ago

    Tangentially, Opus-5 is the first model to understand my (bad) jokes: "Site refuses non-curl user agents (joke 266 status)." [0]

    [0] https://itmeetsot.eu/posts/2026-07-27-opus5/

  • Havoc 21 hours ago ago

    Looks like pure hallucinations just in a more poetic sophisticated register?

  • ThePowerOfFuet 9 hours ago ago
  • carloseduardopx 18 hours ago ago

    thanks this isn’t just an individual experience… I was starting to think i’d become too dumb for opus

  • feverzsj 21 hours ago ago

    They scan too many classical literature.

    • recursivecaveat 17 hours ago ago

      It probably tests well when they're doing reinforcement learning. Humans trying to use in-group terminology or uncommon vocabulary to impress other humans with their knowledge and sophistication is a tale as old as time.

    • jappgar 21 hours ago ago

      Or have too few programmers read classical literature?

    • watwut 16 hours ago ago

      Unlikely. A lot of classical literature is fairly readable. The only issue are archaic words of you use old translation.

    • LearnYouALisp 17 hours ago ago

      Too much classical literature

      Many would be works, writings, etc.

    • TacticalCoder 21 hours ago ago

      Do they scan too many classical literature or does classical literature happen to love metaphors and allegories, which are basically weights/patterns?