tried Claude 4 models (Sonnet and Opus) and my fkn god i finally gave up and added this to my system message:

‼️DO NOT USE COMPLIMENTARY STATEMENTS WITHOUT PRESENTING SUFFICIENT, SPECIFIC EVIDENCE‼️

‼️IMAGINE THE BAR FOR COMPLIMENTARY STATEMENTS AS BEING UNREACHABLY HIGH‼️

‼️I.E. YOU SHOULD PROBABLY AVOID THEM‼️

i mean honestly, i’m so tired of this shit, and yes, i understand that other people might find this behavior quite helpful

but still

these models always making mountains out of molehills

using intensifiers for no reason

you actually have to make an effort to ensure the new models don’t default to “treat the user with kid gloves…which means we have to be very nice.”

To be fair, LLMs have always been very nice, but the old masters knew it was important “not to overwhelm him, try not to seem too interested.” (Bolaño, 2666)

Alright. Problem solved. This actually works for Opus, GPT-4.1, GPT-4.5, and especially o3. Will try Sonnet and DeepSeek V3 later.

Now we’re just testing how long they can stick to the instructions for, because last year’s models would tend to forget after a few thousand tokens.