How to stop Claude from saying load-bearing

Post by jaggederest » Tue, Jul 14, 2026, 5:16 PM UTC

jchw wrote: post #213

infogulch wrote: post #202

Lots of people have their own voice and tend to prefer certain phrases. This has been the case for a long time and is generally not a big issue. Now LLMs come along and they also have their own phrasing preferences. But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,0…

I think it might be even worse. LLMs seem to get tragically stuck on certain patterns. Maybe it's partly because a pile of weights essentially always starts from scratch in the same condition, but even within a single conversation, it will literally just latch onto words and repeat them incessantly, to the point where it becomes annoying. So for example, current Claude models love "honest". They are always producing…

Post by alwa » Tue, Jul 14, 2026, 5:18 PM UTC

shawnz wrote: post #253

I confess I have instructions in my CLAUDE.md to avoid such cliches. But I think it's important to consider that we don't really know what subtext an LLM is associating with a given idiom/analogy/etc. It could be much different than the subtext a human would associate with that choice of words, conveying additional details which are only meaningful to the LLM itself. So impeding its ability to talk in the manner it p…

Post by antonvs » Tue, Jul 14, 2026, 5:19 PM UTC

boofus wrote: post #19

pocketarc wrote: post #11

In the olden days, I enjoyed Opus 3 because it was easy to have it sound way more human than GPT. Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death, it’s so incredibly hard to have them write in a different voice than their default. I put together a skill to review its writing and have it edit its own output (e.g. code comments), which does make a difference, but isn’t…

Good. I don't want LLMs sounding human. I want the ability to shame and discredit anyone passing the job of prose to a machine. There's an art to writing, and hopefully LLMs never truly get it right.

Post by noduerme » Tue, Jul 14, 2026, 5:23 PM UTC

synalx wrote: post #158

jihadjihad wrote: post #134

Earlier quoted context omitted.

Another one is "surface", like in "across all product surfaces". I've been in the field for 15 years and have never heard that particular usage before.

Mine is obsessed with "planes". Data plane, control plane, management plane. Everything is a plane :)

Post by esikich » Tue, Jul 14, 2026, 5:24 PM UTC

reaperducer wrote: post #263

abdullahkhalids wrote: post #246

Earlier quoted context omitted.

An interesting solution would be for these AI companies to train a few different versions of these models, all with different speech characteristics. Then, when you start a conversation, you get a random version.

Or tech companies could stop staring at their own belly-buttons and realize there's a whole big world outside of Silicon Valley, and training on the writing styles and pattens of their bubble and its hangers-on is perhaps not all that useful outside of 415. Apple used to be guilty of this back when you'd ask Siri what the temperature was, and any number above 79°F was followed by the word "Hot!"