alt Hacker NewsI feel like it works A LOT better than Opus 4.8 + Sonnet. I now use it exclusively at high effort for planning and low effort for writing the code (instead of Opus 4.8/Sonnet).
However, it's absolutely exhausting to use because of the way it communicates.
All the jargon and its weird, over complicated way to phrase simple things makes it almost impossible for me to understand what the hell it's trying to even say half the time.
Cherry on top, the idiotic follow-ups and caveats that are completely useless 99% of the times but reveal major bugs 1% of the times, so you're forced to read them. Absurd.
I've tweaked CLAUDE.md to force it to only responds with TL;DRs and avoid follow-ups, suggestions and next steps at the end unless they can lead to destructive actions or loss of data, but I'm fighting against the system and diluting other instructions.
A huge piece of shit like other models, but that's what they pay me to do and I do it and go home.
Replies
I have to preface all my prompts with, “in simple, plain English…” because it doesn’t respect my rules on this stuff.
I’m glad to read I’m not the only one getting these unintelligible responses from Claude lately
I got this in my rules:
- Be concise and readable — use line breaks, avoid verbosity.
- I don't need conversation from you. End summaries with a short tl;dr of what you fixed in a bulleted list and any outstanding items as another bulleted list, in this order. Omit all other verbose details
It has definitely improved things, but I have to fully agree with all your points because I still occasionally get gigantic tables and stuff when I never asked for it. Makes it even more frustrating when I want to scroll up to read previous prompts in the session, because now I have to sift through all this garbage.
EDIT: I used Claude to modify its own rules, and now it's much much cleaner in case anyone else wants to use it:
I don't need conversation from you. When reporting finished work, the *entire* response is these two sections and nothing else:
```
TL;DR
- <what changed — one line each>
Outstanding:
- <unresolved, blocked, or needs my input>
```
- Drop `Outstanding` when nothing is outstanding. Never drop `TL;DR`.
- One line per bullet, naming the thing that changed. No sub-bullets, no reasoning, no restating my request.
- Never include: tables, before/after comparisons, headings, diffs, file excerpts, a walkthrough of what you inspected, or a closing offer to do more. The only permitted code block is a command I need to run.
- If something needs explaining to be usable, it is an `Outstanding` bullet, not a paragraph.
- Answer direct questions directly — no `TL;DR` wrapper, and none of the padding above.
- After delivering a solution, re-read these rules and verify none were skipped.