loopmonster

This is unreadable

> "Forty percent chance of precipitation." I never understood what forty percent of rain meant.

You don't understand the world's most understandable statement?

> On Monday my manager wrote in the team chat: "On Friday we'll discuss roles." No emoji. For three days I wondered what my role was.

Three whole days with no contact with your manager at all? Zero opportunity to ask anything amongst all the other activities and communication?

> And now I remember the whole morning minute by minute

You have a perfect-as-if-traumatic memory of specifically the day that your manager sent a cryptic message in chat that you didn't follow up on for three days?

> With a shirt, at least, everything is defined: here's the collar, here are the sleeves, here's the crease that shouldn't be there.

Oh, you're going to love when you discover other objects. Just you wait.

Every click of my mouse wheel takes me epilepsy-fast through about 10 articles.

I don't know that that analogy fits for this comment. The argument is that the old skill is genuinely no longer needed in favour of the new skill, but the new skill requires experience from the old skill. I don't think being a good driver needs you to have already been a good cyclist.

Okay: { heads: 0.5, tails: 0.5 }

Is biomimetic dentistry a red or green flag?

If the second LLM is just describing the content of the commit doesn't that defeat the purpose of the description, to capture the context that doesn't make it to the code?

> It’s one of the really famous cartoons. If you’re reading this newsletter, you’ve probably watched it yourself.

I've never heard of it and would have appreciated at least a cursory definition. I thought I was going to see an article about an ad for Opera the browser.

That's the sharpest point anyone has made in this thread so far, and it reframes the entire conversation.

Because it's about AI

Why are you doubting me? Have you tried Opus 5 yourself?

It's the output.

I think Opus 5 might have crossed the line on this where Opus 4.8 just barely didn't. Working with Opus 4.8 came to feel pretty natural eventually, but I hate working with Opus 5. I'm always telling it to go back and rephrase basically everything it said. And it doesn't even answer my question without burying it - it outputs reams of babbling and summarised summaries upon summaries, and if you glance at the shape of what it's saying it looks like it's being thorough or that it's found useful new info, but it's never actually saying anything. It's like it gets caught in a loop of self-congratulation over what it said before.

Making the experience more hostile for the human feels exactly like what it's doing, but I don't think that's intentional, I think that's a side effect of newer models being optimised for agenticness. No one is benchmarking DX.

The fact that you've been posting this idea into the void for 8 months with no pickup is already your answer

But that page is also obviously written by AI. How do I know it's actually meaningful and not retroactively justified from the agent already having been instructed to create the project?

AI prose is great at celebrating whatever you told it to celebrate, but it always misses the most important detail: why should I care?

To be fair, even if I have to look up half the words in the post to understand what he's trying to say, 'Do not use a thesaurus' still has weight - it's one thing to already know the perfect word for what you're trying to say (even if many others don't know that word), but another to decide on a whim that a given word should be replaced with a more 'advanced' alternative without knowing what you'll find or understanding the nuances of your pick.

Loving the collage of screenshots where every one screams of being AI generated

The only ones in the readme that don't feel like slop, to my eye, are Cold Snap and Mend Assembly - I like those. The rest are all practically identical and are the go-to output for what you get if you ask Sonnet to build a website.

This line made me think by 'normal coding work' the author means doing something they don't understand well enough to be able to distinguish the models' output.

On mobile the scrolling part of your UI is about a centimetre at the bottom of my screen

The post you're replying to didn't say that, but regardless, I would say 'thinking aloud' is a pretty good descriptor for the word-by-word narration kind of thinking where you sort of both say and hear it in your head. I have heard that some people who who experience 'inner monologue' experience their thoughts nearly exclusively like this.

It was the content. So many very specific claims with no source, just stuff being made up. I don't know who Brené Brown is, perhaps she specifically researches trust, but how curious that her daughter can raise a problem with trust, specifically cite two named behaviours that build trust, and then Brown just happens to have a database of trust-building behaviours to hand, that she hasn't even analysed, ready to output a teachable moment.

Even though they were fully booked from the phone bookings regardless

Welcome to the UK, enjoy your stay

I'm yet to be invited to the celebrations.

Most of the things on the linked doc's list of things Claude Code can't do, it definitely can.

You could consider it a jigsaw puzzle game.

insights is straight ego fluffing - it just tells you how brilliant you are and the only actionable insights are the ones hardcoded into the skill that appear for everyone. things like be very specific with the success criteria ahead of time (more than any human could ever possibly be), tell the llm exactly what steps to follow to the letter (instead of doing those steps yourself), use more skills (here's an example you can copy paste that has 2 lines and just tells it to be careful), and a couple of actually neat ideas (like having it use playwright to test changes visually after a UI change)