Type in a single letter and watch how much it milks just that
Claudette: Make Claude stop talking like a BuzzFeed article
161–170 of 254 posts
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#162Hmm. I took a look at my claude output and I don’t see anything remotely like that in my responses. Occasionally a bit verbose, but none of this but “here’s the kicker” thing that the post claims, although I also notice that I’m using Sonnet which seems to be just fine.
Opus 5 is particularly bad. Opus 4.8 to a lesser extent. It was extremely clear by the code comments in my colleague’s PRs.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#163Earlier quoted context omitted.
And will reference transient working docs in code comments. // No retry was added here per AC 37b in FEATURE.MD.
// 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.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#164I've started giving these instructions and I think I've been much more successful in generating clear output: Comment blocks are Limiting the number of words is the strongest factor in cleaning up the output, IMO. For older code I've instructed it to delete all the comments, and then I re-comment it using a new session and these guidelines, asking it to rejustify the need for every comment to itself.
I have extended this to coding work as well. "Implement this plan in less than 1000 added lines, tests included". It's amazing how well-behaved and concise models can be with simple guardrails.
Of course, you have to intuit a reasonable line length, but Claude cries if you happen to clip its wings too aggressively.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#165Earlier 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???
// Workaround because we don’t have an age column in the db. See JIRA-1234
This would be better IMO :)
Most of the context belongs in a ticket. And the difficulty is subjective!
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#166Has 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.
Watermarking? It certainly is useful for that. I see Claude-written prose AND I know instantly it's LLM writing. What I do with that knowledge varies.
Gemini has been watermarking for like a year and doesn't have the same problems.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#167Every time I engage with Claude I am reminded how bad it is at communicating to its human.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#168Earlier quoted context omitted.
I have no Claude.md file. Claude is still absolutely horrible.
If you’re on Claude.ai web, you still have preferences tied to your past interactions. That can be edited.
I run everything sandboxed within a custom environment, no history, no memory, no autoloading of tools. Vanilla Claude experience.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#169Earlier quoted context omitted.
Idk if you’re coming up with these on the spot but they’re linguistically fascinating.
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.
Re: Claudette: Make Claude stop talking like a BuzzFeed article
#170Earlier quoted context omitted.
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???
// Workaround because we don’t have an age column in the db. See JIRA-1234 This would be better IMO :) Most of the context belongs in a ticket. And the difficulty is subjective!
I'm mostly writing code for myself, but it's a project that'll end up being public and it'll be available for others to do whatever they want with. Does that change the answer?