pull down to refresh
reply
Paste this at the end of every prompt you send out (when you're satisfied, put it in CLAUDE.md/AGENTS.md/rules/whatever you use):
**IMPORTANT:** Keep paragraphs to 2–3 sentences max, separated by blank lines; use headings, short bullets, and bold key terms so the answer is skimmable. Prefer several small paragraphs over one long block — never write a wall of text.
**IMPORTANT:** Write code comments that explain the code itself; never reference plan files, task docs, chat history, or anything outside the repo (no "as per plan.md", "per the spec above", "step 3 of the plan").reply
I'll try this out in a few minutes, thank you! I've been doing this manually, but not with these words, and it's always a lottery.
Maybe I just got spoiled by the way LLMs used to talk i.e. with lists and spacing. People criticized it, me too, but it was actually comprehensible.
Anthropic must do something about the multi-page paragraphs that its models produce. I have always had trouble focusing while reading (in my life), often having to reread the same lines, but this is just unreadable and kinda unfair.
I have to use GPT to decode whatever Claude yapped about, or write things myself.
edit: yes of course there are skills but it's clear that after 4.6 the focus shifted on maximizing LLMs performance by writing what the LLMs can comprehend better - and it makes sense, how else are we going to retire humans?