lowenbjer

Ah, nice analogy! The way you describe it makes sense, I need to read up on the topic. Chain of Thought, is that what I should look for?

Yeah i tried that but I did not get it to work consistently.

It feels like it took the styles as suggestions rather than rules to enforce.

How has it been working out for you in longer conversations?

I too think there is a fallacy in automatically attributing longer texts to hold more information.

While i understand your reasoning here, and while I can't produce any proof that that supports my claim that it doesn't, I still would like to share my experiences after using terse personally for a couple of weeks, and those are that I have not noticed the degradation in output quality that you are describing. Quite the opposite, as my interactions use up less context space, my guess, i find that accuracy has increased rather than decreased.

How so?

Yes, exactly that, so there's refined writing instructions in the system prompt and a reminder with a compact version of the rules injected every turn from a UserPromptSubmit hook.

I agree, how i use it i don't want it to be creative or help me think unless i ask it to do so. I'm using it to DO work.

Yes! Some of my benchmarks was against Opus 5.5, and it reduced output over 50% on vanilla settings. Check repo for data.

Fair enough! Can't argue with that

I tried tidal for the Lossless (dont care about the 24bit, i care about no EQ and compression added to music) but i went back to spotify for their recommendation model. Its a moat for me.

Fair point, for me there is no scrolling required though, its like nr 3 in the list.

I wonder how long it will take for AI to learn how we work with software on an individual level and adapt the UI to fit our usage patterns.

I get that it looks bad to have vibe coding bugs creeping into your codebase for such a big company, but isn't it common sense that owning your misstakes taking accountability for them generates respect?