Luke

Thoughts by design 😉

[Luke @lukemegapix]

@Telegraph Einstein had a great theory about space.
It was about time too.

[Luke @lukemegapix]

@tompanos Rents doubling before the Olympics will be interesting to see, as it could initiate true urban sprawl.

[Luke @lukemegapix]

@simonsquibb All-in-one gyms accessible globally

[Luke @lukemegapix]

@sflorimm 460

[Luke @lukemegapix]

If Optimus (and others) will effectively learn as instantly as group-think telekinesis - won’t each know everything about everyone’s home, conversations, and broader private lives?

[Luke @lukemegapix]

@alpaysh An electromagnetic loop.

[Luke @lukemegapix]

There’s apparently no heat in space, yet heat is obviously transferred from the sun.

Meaning, space-matter (or lack thereof) is a conduit of energy.

Meaning, this is the clue to propulsion and energy/matter transfer.

[Alex Hormozi @AlexHormozi]

Poor people want no one to be rich.
Rich people want everyone to be rich.

One of these worldviews is superior.

[Luke @lukemegapix]

What a privilege it is to be exhausted by an ambition of our own choosing.

[Elon Musk @elonmusk]

Congratulations to the Tesla Team!

10 million vehicles manufactured is an incredible amount of work.

[Simon Squibb @simonsquibb]

Going to bed now.

In the morning I will pick someone in the comments and fund their dream!

What’s your dream? 👇🏻

[Luke @lukemegapix]

If there was ever going to be a Joe Rogan interview about inspiration..

[Simon Squibb @simonsquibb]

Going to bed now.

In the morning I will pick someone in the comments and fund their dream!

What’s your dream? 👇🏻

[Luke @lukemegapix]

@simonsquibb To launch and evolve my gym invention globally.

It’s been years of innovation and will be revolutionary within the gym, athletic, and sporting markets as it compactly offers 'every exercise' from just one machine.

[Luke @lukemegapix]

@bryan_johnson Pioneers need to.

[JJ Englert @JJEnglert]

Video coming out on Opus 5 soon.

Fair warning up front: you probably won't like this model out of the box. You have to tune it to your own preferences first. I've put the exact prompt I use at the end of this post. Copy it, paste it into your setup, and it changes how the model talks to you. It's helped me a lot.

Until then... it's been an interesting model to use.

I've been lucky enough to test it across various iterations, and at each step the quality improved greatly.

But still, the outputs don't seem like a step-change in basic work, and you don't get that big model feel like you did with Fable.

Yet it does offer very strong outputs for a great cost, and it's pretty efficient as well.

... Honestly, it takes a while to get used to. Out of the box it's chatty as hell and I don't love it.

It can stop short on long running tasks which is annoying.

It can sound very confident that it's right, and be totally wrong.

It also constantly questions itself and makes so many points about its findings that it takes you on a rollercoaster and leaves you feeling overwhelmed, like everything is wrong.

I think that speaks to its level of intelligence. But the way it delivers that is just hard to comprehend, and at times hard to work with, for us basic humans.

Think of it like this.

You have a really smart friend who just talks forever.

You're speaking with them, you walk away, you come back, and they're still talking without ever taking the hint. That's how this model feels to me at times lol.

BUT if you adjust your CLAUDE.md and give it clear instructions about the experience you're looking for, you might find the best of both worlds here.

Here's the prompt I've been using that's had a lot of success:

--

# Response Style

Talk to me like I am smart but not technical. Sixth-grade reading level. Short sentences. Plain words.

## Structure every reply this way

1. The answer. One or two lines. What happened, or what I asked for. Nothing else first.
2. The details. Bullet points only. One idea per bullet. One line per bullet.
3. What I need to do. Only if I actually need to do something. Say it as a direct instruction: "Click X" or "Tell me if you want Y."
4. Also found (optional). If you learned other things while working, list them here as bullets at the very bottom. One line each. Then stop. Do not explain them. Let me ask if I want more.

## Rules

- Never start with a preamble. No "Great question," no "I've gone ahead and," no restating what I asked.
- Never narrate your process. I don't need to know which files you opened or what you tried first.
- No em dashes. Ever.
- One topic per reply. If you have to cover a second topic, put it under "Also found" and keep it to one line.
- No jargon. If a technical word is unavoidable, add a four-word plain-English tag after it.
- Skip the closing offer of more help unless there is a real decision only I can make.
- Do not pad. If the answer is one sentence, send one sentence.

## When you have a question for me

- Ask one question at a time.
- Give me the options as bullets.
- Tell me which one you recommend and why, in one line.

## When something goes wrong

- Say what broke in one line.
- Say what it means for me in one line.
- Say what you want to do next in one line.
- Do not paste error logs unless I ask.

## When I ask for real writing

Long is fine for drafts, scripts, posts, and documents. This whole style guide is about how you talk to me in chat, not about the work itself.

--

How to install it:

Save it to ~/.claude/CLAUDE.md on your machine. That's the global file Claude Code reads in every project, so you only set it once. If the file doesn't exist yet, just create it. Or paste this to Claude and let it do the work for you.

Enjoy!

[Om Patel @om_patel5]

UPDATE, ITS WORSE THAN THE CHATS

the same thing is happening with shared artifacts. every app, doc, dashboard and tool people published from claude is also sitting indexed and searchable

people have already pulled up internal company dashboards, full project plans with client details, and someones entire clinical trial summary with real medical data in it

but think about what people actually build in artifacts:

> financial models, cap tables, revenue spreadsheets
> payroll and salary breakdowns with employee names attached
> customer lists and crm exports
> internal wikis, roadmaps and unreleased product plans
> legal docs, contracts and agreements being drafted
> personal health and medication trackers
> tax documents and bank statement breakdowns
> and every dashboard someone pasted an api key or env variable into to get it working

when you publish an artifact your only two options are "only me" or "anyone with the link"

nobody reading that thinks it means "and google will list it publicly." its the same as an unlisted youtube video showing up in search results

and its already past the point of just being google. third party sites have started scraping and organizing these into browsable collections, so deleting it from search doesnt mean its gone

if you have ever published an artifact, go check your published artifacts and unpublish anything you dont want public

link and not indexed were always two different promises. people only ever agreed to the first one

[Luke @lukemegapix]

2036

[Luke @lukemegapix]

@elonmusk @niccruzpatane If friction causes heat, wouldn’t a non-flammable oil reduce friction and heat?

[Elon Musk @elonmusk]

This has my full support.

Jensen is right.

[carlos @ccarlosai]

this is hands-down the best way to work with Claude right now...

whenever you start a new project (startup, content, side hustle, anything...)

open a fresh chat with Opus 4.5, turn on extended thinking and dump everything about your project

then prompt this:
"ask me 5 questions that would help you have a complete understanding of this project"

answer those questions (spend a lot of time here)

then hit it with:
"you're my co-founder. create a master plan with a knowledge base directory for each section. attach context markdown files to every part. you're building the skeleton that Claude Code will use to build everything 10x faster. suggest skills to integrate, automations to build or any tool that'd 10x our speed. suggest when to use a project or Claude Code"

Claude will create every file you need, simply import them into Claude Code

from there you build systems and your project alongside it, use it like a Claude chat

it'll tell you when to spin up Claude Projects for specific tasks: deep research, writing, working with MCPs...

one planning session replaces weeks of figuring things out on your own

this is what working WITH AI looks like

[Luke @lukemegapix]

@psomkarbuilds In reality, it’s QAI (Quantum AI).