The Output Style, It Does Nothing! - Learning to live with Claude | atomic14

🌈 ESP32-S3 Rainbow: ZX Spectrum Emulator Board!<br>Get it on Crowd Supply →

The Output Style, It Does Nothing! - Learning to live with Claude

View All Posts

read

Want to keep up to date with the latest posts and videos? Subscribe to the newsletter

Posts ·<br>Videos ·<br>ESP32 ·<br>Tools ·<br>Support

« Rescuing my 2006 Travel Blog

HELP SUPPORT MY WORK: If you're feeling flush then please stop by Patreon Or you can make a one off donation via ko-fi

Here’s a response Claude came up with recently. I was asking it to review some of the code it had been writing for my “Open Vibe Code” Elite clone - you can play it here in your browser, it’s surprisingly good.

“Twenty-seven echoes; most are two halves of a seam stated from each side, which is correct. Four are true duplicates. Checking two of them:”

There’s a lot of this kind of output coming out of Claude. The internet is full of people complaining. Sometimes reading what Claude says is very much like being stuck at the bar with the world’s most boring know-it-all. Lots of clever phrases and convoluted sentences - but ultimately vacuous and empty.

What’s really interesting, though, is that the code and docs it generates are pretty good (at least the tests are green, the game plays well etc…). It’s just the communication with me that’s the problem.

A popular recommended remedy for this is to change the output style:

Some people suggest using ASD-STE100 - Simplified Technical English. The theory is that this should force Claude into communicating with you in a sensible way.

There’s a bit of controversy over whether you change the output style or you just add it to CLAUDE.md, but whichever you choose, the result is supposed to be substantially better.

Does it work?

At first, absolutely. It feels better - easier to read, shorter sentences, fewer random, weird analogies.

But I think that feeling of it being better is an illusion. You think it’s better because it’s different. It’s just a relief to your brain not having to parse Claude’s madness. But after a while you get used to the change and slowly start to realise that the prose is just as vacuous and empty as before.

And the real kicker… the quote at the top of the page was produced after I’d changed the output style and added it to my CLAUDE.md…

The big question is: Does it matter? And I suspect, probably not.

I’m starting to think of Claude’s ramblings in the same way as the “Thinking…” content - it’s not necessarily meant for me to read. The actual output that matters is the working code. And to get quality there you need programmatic constraints and constant adversarial review.

It’s time to make peace with Claude’s nonsense. Stop reading the prose and judge things purely by the produced artefacts - once you do that, the quality of the commentary stops mattering.

So judge the artefact rather than the commentary. This is what all that vacuous prose actually built:

Harmless is playable in your browser - no install, nothing to sign up to, just open it and fly - and the source is on GitHub if you want to see how it’s put together. Let me know how you get on in the comments.

Related Posts

Related Videos

The Hacker News Effect - The Website Didn't Catch Fire - Let's look at the traffic - Witness the Hacker News effect in action as the author's blog skyrocketed to popularity, easily handling massive traffic thanks to efficient hosting and Cloudfront!

Even more AliExpress gadgets - Another shamelessly overstuffed mailbag—cheers to PCBWay for fueling the bench carnage. I poked UV sensor cards with a curing lamp (they go purple then fade), sifted through robot gears, and lit some fragile LED filament letters (~2.7 V, happy around 100 mA). A USB photocatalytic mosquito trap spins at 0.02 A (teardown later), an OV7670 cam joins the ESP32/UVC experiments, and a chunky COB strip looks like a 12 V amp-gobbler. Bonus: surprisingly decent keyring torches with ‘police’ flash, a hilarious translation on a temp/humidity doodad, and watch oiler wands that are perfect for painting on solder resist—projects incoming.

Most Interesting Addressable LEDs that I've Ever Seen - So, I got this nifty 2x2 meter 400 LED curtain and immediately went to work dismantling it. The LED strands are tapped off the main wire, rather than daisy-chained, which is a departure from the norm. Turns out, these LEDs are pre-programmed, allowing them to intelligently latch onto the right serial data. Unraveling the control unit, we see an IR receiver and other key components responsible for driving the LED strings. Despite my misgivings about deciphering in-built Bluetooth characteristics, I hooked the circuit back up with our dependable WLED software and got some amazing grid patterns. Interestingly, the LEDs operated smoothly at 3.3V. All in all, a fun exploration of hacking this LED curtain.

Automating Blog Improvements with AI: Summaries, Tags, and Related...