I personally got used to the claudisms and think people are making too big of a deal out of it. Yes it says load-bearing and caveat a lot, but at least you know behind the scenes what meaning it's assigning to certain situations.
Claudette: Make Claude stop talking like a BuzzFeed article
171–180 of 254 posts
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#172Has Anthropic said anything about how or why Claude writes the way it does? So many people hate it, seems like they need to do some damage control there. I haven't had the same problems others have but I'm also not a heavy user of it.
It's easiest to explain this while anthropomorphizing the model, I know some folks here hate that, sorry about that. I heard an interesting diagnosis for why Claude does this: the output is a compressed version of its thought traces, very dense because the model is under pressure to use as few tokens as it can and to pack as much (for accuracy) of its concepts into the output. One of the reasons that "don't do X" typ…
Hey Yuri, slight tangent but how did you get to be an investor on those private companies as per your LinkedIn?
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#173I personally got used to the claudisms and think people are making too big of a deal out of it. Yes it says load-bearing and caveat a lot, but at least you know behind the scenes what meaning it's assigning to certain situations.
I kind of wonder if we would have appreciated the verbose prose when these LLMs first came out and out muscles had not yet atrophied. When I do stop yelling at Claude to be more concise and actually read what it wrote it's often valuable complexity and subtlety that I could use to better understand what it did and steer it, rather than Claude just papering over important details like it did before.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#174For those of us who don't want to pay for Gemini tokens, what would be the best local LLM to use for this? (A model that can run reasonably well in a ~24GB MacBook.)
I don’t have a good answer but would like one. I’ve got a not too old desktop with a 4090 and 64gb of ram, I’d like a local model also.
I haven't tried with Claudette but did evaluate https://github.com/zachahn/vomit and https://github.com/gvzdv/claudish-to-english earlier today. I ended up using claudish-to-english with a prompt derived from the vomit one and some of my existing instructions. I ran a few local models through a test harness to see how they did, and the gemma4 ones added bad behavior back in less than any others I tested.
So for the parent's Macbook question `gemma4-26b-mlx` should work well.
For you with 24 GB VRAM, `gemma4-26b-a4b`. I tried higher VRAM models and they slowed down while still doing just as well or slightly worse.
If someone else tests and finds a better performing model though, please update me here, I'd love to try it.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#175Earlier quoted context omitted.
Claude not only writes verbose comments, it also writes comments about how things used to work when refactoring. That might have a place in version control comments, but not in the code.
And will reference transient working docs in code comments. // No retry was added here per AC 37b in FEATURE.MD.
This one drives me nuts, especially because I divvy up plan documents into such granular sub chunks and Ralph loop over them, I get nonsense commit messages and comments like “PLAN-5.1.A.d.42 load bearing reassertion” unless I AGENTS.md to hell and back… and still end up having to manually reject 5-10% of commit messages because the agent simply forgets AGENTS.md instructions until reprompted.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#176Earlier quoted context omitted.
Came up with them on the spot. Unfortunately, I've been working with Claude so much it's like my brain can autocomplete them natively.
it's not just you, there is research that people are starting to talk more like chatGPT. you have a gift for parody though.
That's a sharp insight, and it reveals something core to communication that I otherwise wouldn't have considered- HN item 6b translocates reliospacactivity of our medium.
Shall I engage the tachyon beams, sir?
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#177Earlier quoted context omitted.
// The lesson from the Parse-dont-fail-era campaign // Judged on merit from computed properties during the cursor saga // Chop 6ms due to lenience and lax-constraints vs 18ms baseline April perf measurements
As a human who isn't a professional programmer, I've been writing comments like, // let's track age!! // this is harder than you'd think as I with totally impressive // foresight didn't add age to the raw data. // // More honestly, I didn't want to add age to the astro data as that's // a calculation that can change depending on how you slice it. // // Hence we need to figure out their age first. Is that bad???
personally it's fine and I've thanked myself many times for overly detailed comments coming up to some from 8 years ago and thinking how tf was I so smart/stupid (depending on the context)
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#178Earlier quoted context omitted.
This! Claude writes comments about how things used to work, which can be useful sometimes, especially if it's a big change that requires one to genuinely consider legacy behavior, but most of the time it shouldn't be there. Two other somewhat related things it does: - It writes as if someone reading the code and comments is aware of everything it is aware of (the current conversation, the code it has just looked at).…
I've gone back to using Opus 4.6. It's quite nice along all these fronts.
How? I tried but got forced back onto 5.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#179Earlier quoted context omitted.
That's interesting but raised the same question, why berate a machine? Either the agent is not a person, in which case, anything it does wrong is your fault. Or it is a person, it can be blamed for mistakes, but then we can't in good conscious use it as a tool.
Berating a real person is often unproductive too, but people do it to make themselves feel better.
But it's at least plausible the person you're berating is responsible for the error.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#180Has Anthropic said anything about how or why Claude writes the way it does? So many people hate it, seems like they need to do some damage control there. I haven't had the same problems others have but I'm also not a heavy user of it.
I think it's reinforcement learning. It's been trained to give coding results but some of the conversation it gives as a side effect of its coding are absolute garbage