cullyn

universal constructor

[cullyn @cullyn]

matter is to spacetime
as identify is to emotionspace

where valence, arousal, and agency are the emotion dimensions.

related: electromagnetic field is analogous the "affective" field

where novelty and meaning appear distinct, but are unified as a field in emotionspace.

[cullyn @cullyn]

instead of defining what you want to see, what if you defined what outcomes to optimize?

rotations (maybe changes primary accent theme) between "modes"

- current events
- explore your network graph
- quick entertainment
- deeper discussions

the algorithm should determine what variety of things interests you, you just say the dimension to focus on.

[cullyn @cullyn]

@gregisenberg easy fix: algo should insert them into your feed until you remove them.

[cullyn @cullyn]

@VictorTaelin I have mode called "Drive" that i am now defaulting to.

it orchestrates sub agents which also orchestrate their own sub agents whom are dedicated to buildling, reviewing, or planning.

Enables very long sessions with out compaction or large context windows.

[cullyn @cullyn]

@StuartJRitchie I wonder what the reception would have been if it was an X article

paywall means most did not read it, instead probably just that one screenshot of it.

[cullyn @cullyn]

@Alejandro_DPG @atmoio i like to think of it as a text-based accent

capitalization rules mostly just made up. essentially vestigial rules that served a purpose when text was more dense and compact

lower case signals online culture association, stream of thought, not rigid corpo-LinkedIn culture

[cullyn @cullyn]

i've always thought digital brain uploads would require fancy tech that decodes the biological brain; always pondering the feasibility and fidelity of it.

i haven't considered, until now, that the upload could be slow & indirect.

instead, what if it's a network of compounding digital snapshots of our attention.

not a clone.
not an upload.
just ... another evolving layer?

a layer built on a different substrate. one that allows our thoughts to echo, morph, and interlink in a similar way they do in our wet brain.

if enough information is captured and organized in an increasingly sophisticated LLM managed second brain....

then how long until this second brain can produce outputs from novel stimuli that would be on par with what your biological brain would produce?

would that count as a digital upload?

could it capture your tastes?
your intuition?
your... subconscious?

it will probably never be a 1:1, since your silicone LLM powered second brain would be smarter and more capable.

but at what point is it theoretically... you? what is enough?

surely it will remain an extension of you, or rather, a symbiosis. but remove the engine.

disconnect the LLM.
sedate the brain.

what is left is an artifact.
what if left ... is you?

[cullyn @cullyn]

Claude mythos security capabilities introduces weird dilemma for updates:

1. not updating quickly now puts you at risk for various zero days being found and fixed

2. updating immediately puts you at risk for increasing surface area of supply chain hacks to sneak in

interesting times

[cullyn @cullyn]

@HankFrank I would buy a whoop again if I didn't have to have a stupid subscription. I don't need a fancy analysis or app.

it was the pretty accurate and I don't want to wear a big watch.

> me and literally everyone I talk to about who **has had** one.

no one has them anymore.

[cullyn @cullyn]

@ThePrimeagen @xaskdev I tried checking it out, but couldn't even sign up for paid?

are you grandfathered in?

or am I just dumb and didn't setup right

[cullyn @cullyn]

@aakashgupta make ads cheaper on lower ratio content?

or more expensive on quality content

win-win

[cullyn @cullyn]

@arscontexta should be more like sleep phases:

deep → clean up accumulated slop, duplicated mess

light → consolidated, reorganize architecture, general high level planning

rem → play with high temp, generate novel ideas, simulate recent sessions with different parameters

[cullyn @cullyn]

there will always be problems to solve

if there wasn't, well then... that'd be a problem

[cullyn @cullyn]

@reviewbyslaide @mattpocockuk tasteless used here (I think) is defined as inability to naturally do or lack of intuition.

this means he is steering the model with additional instructions or review is needed.

still possible to achieve a good result, just harder

[cullyn @cullyn]

@signulll more excited than ever

I feel like there is so much power just waiting to be channeled towards any endeavor I want

there will always be problems, engineering has always been about solving problems

[cullyn @cullyn]

@dl_insider @marlowxbt this makes the most sense

[cullyn @cullyn]

@0xSammy @0xsamgreen https://t.co/OwVAAVtu3T

[cullyn @cullyn]

@Carter_OW could be evil, or they could be losing money as a marketing method?

then adjusting to a sustainable price?

I lean towards it likely being exploitive practice (especially with tip observation), but always good to try to make a good faith argument.

[cullyn @cullyn]

@elonmusk @Scobleizer @nikitabier wonder how true this is:

→ "algorithm sucks"
→ makes algorithm better
→ dopamine rush, amazing, spends more time on x
→ slow news week, no drama.
→ withdrawal, "algorithm sucks"
→ makes more engaging, accidentally incentivize slop
→ unhappy engagement
...
repeat