Heinrich

building ai knowledge systems with @arsumbrisai

[Heinrich @arscontexta]

https://t.co/6tlINvABZ9

[Heinrich @arscontexta]

@ulriksparboe @arsumbrisai learned a lot from the early feedback. back to building now. wont be that long this time

[Heinrich @arscontexta]

going quiet for a few weeks to focus on the next big @arsumbrisai update. stay tuned

[Heinrich @arscontexta]

sometimes what feels like a pivot is just a shift in perspective that helps you understand what you were trying to build all along

[Heinrich @arscontexta]

@kaoshedge @arsumbrisai its on our list, will keep you updated

[Heinrich @arscontexta]

sometimes what feels like a pivot is just a shift in perspective that helps you understand what you were trying to build all along

[Heinrich @arscontexta]

@samhbarton @nateliason @arsumbrisai nice! yeah feels like a dream tbh

dogfooding loop is insane if you build knowledge / agent infrastructure yourself

[Heinrich @arscontexta]

@nateliason @arsumbrisai https://t.co/R6NvG3rS24

[Heinrich @arscontexta]

https://t.co/6tlINvABZ9

[Heinrich @arscontexta]

@nateliason @arsumbrisai https://t.co/6ihRqiQR4g

[{ I N P U T } @lt0gt]

technical overview of @arsumbrisai

- many repos of md + yaml → one typed graph
- type refinements, cross-repo types
- lists, tuples, inline vs [[linked::repo]] refs
- abstract, sealed, unions, intersections
- typed md bodies, location rules, meta
- au-host: views as typed projections
- au-mcp: tools/hooks/skills as typed plugins

[Heinrich @arscontexta]

@KacperKazan @hamiltonulmer @arsumbrisai i love that!

[Heinrich @arscontexta]

@kamil_k https://t.co/2M1FTBmzGi

[Heinrich @arscontexta]

i wrote 20+ atomic writing rules ( see 🧵 )

each in its own md file explaining what matters to me and why

i mean “explain this in ASD-STE100” is a start...

but i want to define my own writing style and carry it across models and sessions

session profiles select which rules get injected through the session start hook

i rather work with small composable rules instead of one giant agents md

btw the same rules also power two skills:

/apply-writing-style to rewrite existing text

/check-writing-style to review it against the rules

so i can add one rule, reuse it across profiles and have the next session work with the updated version

the types, rules and skills are bundled as one reusable repo

i can add it as a dependency to my current workspace to make use of it

or i just depend on the types to build a different rule set / profile and reuse the skills

( so in love with composable repos for knowledge work )

check out my writing rules and steal what you like

[Andrej Karpathy @karpathy]

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:

Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:

Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:

Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!

In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

[Heinrich @arscontexta]

@edtadros nice! indeed, so much nicer to maintain and extend. cant go back to huge md files anymore

[Heinrich @arscontexta]

what you are describing is definitely among the things we are trying to solve with arsumbris

its not yet plug and play at the moment, but we have lots of plans to support these sorts of workflows with first party packages soon

at the moment, i think you can probably get quite far by hand rolling some things you need inside of arsumbris

lets chat about this via dm

[Heinrich @arscontexta]

@arpxspace love to hear that!

[Heinrich @arscontexta]

@signulll but who defines the feed algo? should stay a users choice

[Heinrich @arscontexta]

@theo curious about the DAU

[Heinrich @arscontexta]

jump to the first post in case you want to bookmark this
https://t.co/dNggGZYoTR

[Heinrich @arscontexta]

i wrote 20+ atomic writing rules ( see 🧵 )

each in its own md file explaining what matters to me and why

i mean “explain this in ASD-STE100” is a start...

but i want to define my own writing style and carry it across models and sessions

session profiles select which rules get injected through the session start hook

i rather work with small composable rules instead of one giant agents md

btw the same rules also power two skills:

/apply-writing-style to rewrite existing text

/check-writing-style to review it against the rules

so i can add one rule, reuse it across profiles and have the next session work with the updated version

the types, rules and skills are bundled as one reusable repo

i can add it as a dependency to my current workspace to make use of it

or i just depend on the types to build a different rule set / profile and reuse the skills

( so in love with composable repos for knowledge work )

check out my writing rules and steal what you like

[Heinrich @arscontexta]

# Avoid the overused phrase

A overused phrase is one you have read many times.
The reader skims past it.

Write it in your own words instead.

If a phrase comes to you too easily, it is worn out.
Cut it or replace it.

[Heinrich @arscontexta]

# No period on a list item

A list item takes no terminal period.
The bullet and the line break already close it.
So the period is a redundant mark.

Drop it from every bullet and every numbered step.

Running prose keeps its periods.
A sentence still needs its end.

The bullet "read the note." becomes "read the note".

To check, no list item ends in a period.

[Heinrich @arscontexta]

# One word, one meaning

Pick one word for a thing.
Use it every time.
Do not use a synonym to vary the prose.

A reader who meets a second word asks if you mean a second thing.

Use "check" every time.
Do not mix it with "verify" or "confirm".

Scan a note for two words that name one thing.
One of them is redundant.

[Heinrich @arscontexta]

# Cut what could go anywhere

A sentence that fits any note says nothing about this one.

Test each line.
Could it move unchanged to another project or product?
If it could, it is filler.

Cut it or make it specific to this note.