maphilo

Math teacher by day, trying to figure out my superhero identity.

Notion template shop:

[maphilo @_maphilo]

Starting a thread of threads, just so I can find my own stuff;

[maphilo @_maphilo]

@Rainmaker1973 Hope it turns out well!

[maphilo @_maphilo]

What we call ‘bullshit’ at work: is the part of the maintenance work of keeping system running.

[maphilo @_maphilo]

Go home early.

[Massimo @Rainmaker1973]

Only 3 words

[maphilo @_maphilo]

“Why?”

“Why not?”

https://t.co/wj6eRPE6OE

[maphilo @_maphilo]

"I know that I'm dying correctly."

[Sama Hoole @SamaHoole]

Dietician: "Congratulations. Your diet is almost perfect. Whole grains, legumes, seasonal vegetables. Very heart-healthy."
Medieval English Peasant: "I have scurvy."
Dietician: "The fibre content alone..."
Peasant: "My teeth fell out last winter."
Dietician: "The complex carbohydrates..."
Peasant: "I have not eaten meat in four months. I dream about it."
Dietician: "Red meat is not necessary."
Peasant: "My children are small. They do not grow."
Dietician: "They're getting excellent plant protein."
Peasant: "They are getting rye bread and pottage. The lord ate beef last night. We could smell it."
Dietician: "His diet is actually worse for him."
Peasant: "He is six feet tall and has all his teeth."
Dietician: "But his cholesterol..."
Peasant: "I do not know what that is. I know that I am dying correctly."

[maphilo @_maphilo]

This is a thing if you don’t control your boundaries.

What’s equally or more dangerous is the sense of wonder of what more you can do.

[Zara Zhang @zarazhangrui]

Almost every AI power user I know is MORE stressed and busier after using AI, not less

What people thought AI would do: 10x productivity so that we can finish work earlier & relax more

What it’s actually doing: 10x productivity so that we end up with 20x more things to do cos of the sheer possibilities

[maphilo @_maphilo]

You can just do things.

[Séb Krier @sebkrier]

This is wild. https://t.co/fA4oTX8fB9

[maphilo @_maphilo]

This is the key to learning also. Can’t learn when you’re still getting over the setback.

[Sahil Bloom @SahilBloom]

The ability to quickly reset and recover. From a bad interaction. From a bad day. From a missed workout. From a poor decision. You can start over whenever you want. You can't always control what happened, but you can control how long you carry it.

[maphilo @_maphilo]

“The abstraction is a tool, not a destination.”

[Garry Tan @garrytan]

People get high on abstraction too early. They want the system before they’ve earned the insight.

But the good abstractions are never designed. They’re discovered. You do the stupid manual thing enough times and the real bottleneck just emerges. Your initial agency might be driven by a hunch you had in the shower, but that moment won’t get you all the way to making something people want. The right way to make anything is forced on you by reality: what are the real jobs to be done? And what sequence?

This is why “do things that don’t scale” still hits, especially now when AI makes it trivially easy to scale things that probably shouldn’t be scaled yet. PG’s point was never about suffering. It was about contact. When you’re the one manually doing the loop, you see the edge cases. The weird user behavior. The failure modes nobody designed for. The hidden dependencies that only show up at 2am when some flow or intermediate step breaks in a way you didn’t anticipate. If you automate before you have that contact, you just scale your misunderstanding faster.

When the machines can help you vibe code perfection it gives you a false sense of power. I love that feeling as much as you do. But fuck perfection. Do it live. Be the loop.

Feel every friction point. Notice what’s actually true every single time versus what just looked true because you hadn’t seen enough cases yet. Formalize that. Build the recursive version. Then keep checking that your abstraction is still attached to real humans and their needs. Because reality drifts. Your users drift. The ground truth changes under you. You may think you understand but no plan survives contact with the real users and what they want. You find those body blows in analytics and user feedback and we call them the roadmap.

Humans left with not enough data hallucinate too. But just like the LLMs with enough data you unlock real transcendence. Real utility. Prosperity for humans in real life.

The abstraction is a tool, not a destination. The moment you forget that, you’re cooked.

[maphilo @_maphilo]

What we need is more guidance on how non-technical people can use Claude Code.

[Zack Shapiro @zackbshapiro]

https://t.co/QVaE6niDY2

[maphilo @_maphilo]

@bran_don_gell @NotionHQ Would definitely be interested in how you organise your workspace agents!

[maphilo @_maphilo]

Claude Cowork creates the best results with style guide insertion so far

[maphilo @_maphilo]

Testing workflow on generating EDITABLE slides in LLMs

[maphilo @_maphilo]

3/ Test results

1. ChatGPT screws up basic shapes.
2. Claude sticks to rectangles and colours. Aesthetic is simple and clean.
3. Gemini has the best results so far.

[maphilo @_maphilo]

@Nicolascole77 books~

[maphilo @_maphilo]

so... we can just repeat our questions even in chats?

[BURKOV @burkov]

LLMs process text from left to right — each token can only look back at what came before it, never forward. This means that when you write a long prompt with context at the beginning and a question at the end, the model answers the question having "seen" the context, but the context tokens were generated without any awareness of what question was coming. This asymmetry is a basic structural property of how these models work.

The paper asks what happens if you just send the prompt twice in a row, so that every part of the input gets a second pass where it can attend to every other part. The answer is that accuracy goes up across seven different benchmarks and seven different models (from the Gemini, ChatGPT, Claude, and DeepSeek series of LLMs), with no increase in the length of the model's output and no meaningful increase in response time — because processing the input is done in parallel by the hardware anyway.

There are no new losses to compute, no finetuning, no clever prompt engineering beyond the repetition itself.

The gap between this technique and doing nothing is sometimes small, sometimes large (one model went from 21% to 97% on a task involving finding a name in a list). If you are thinking about how to get better results from these models without paying for longer outputs or slower responses, that's a fairly concrete and low-effort finding.

Read with AI tutor: https://t.co/MipHHO6rjX

Get the PDF: https://t.co/XQrqiaGwIO

[maphilo @_maphilo]

What we know how to do is a lot less than what is within our ability to do.

[maphilo @_maphilo]

Something which conflicts with conventional education advice

[Cedric Chin @ejames_c]

One of the things I’ve been grappling with is the idea that clear feedback produces students who can’t sensemake from their own experiences.

That hobbles them somewhat in life.

Reflecting on your own experiences is a skill, like any other.

[maphilo @_maphilo]

@Remotion Clearly there's still a lot to pick up....

[maphilo @_maphilo]

Playing with @Remotion with:

"show the dangers on not decluttering with the use of chicken little"