Mirrorfields
@mirrorfields.bsky.social
I'm sure you remember me
He/it
🔞
He/it
🔞
Reposted by Mirrorfields
flauntology is dual to hauntology
flauntological
February 13, 2026 at 7:50 PM
flauntology is dual to hauntology
Reposted by Mirrorfields
the Tobin Unit is the unit of minimal forward progress on a project. if you do a Tobin Unit on your thing, you moved it forward and are good. feeling anxious and avoidant about a project? open that sucker up and do a Tobin Unit. maybe you moved a comma. great! now you are in good standing
October 22, 2024 at 12:45 AM
the Tobin Unit is the unit of minimal forward progress on a project. if you do a Tobin Unit on your thing, you moved it forward and are good. feeling anxious and avoidant about a project? open that sucker up and do a Tobin Unit. maybe you moved a comma. great! now you are in good standing
okay so, i've been burning *a lot of tokens* today but i now seem to have
- a personality format (with a spec) that seems to create extremely strong, extremely stable attractor basins
- experimental proof that directives in the personality file can still be overridden from within context
- a personality format (with a spec) that seems to create extremely strong, extremely stable attractor basins
- experimental proof that directives in the personality file can still be overridden from within context
February 13, 2026 at 3:49 PM
okay so, i've been burning *a lot of tokens* today but i now seem to have
- a personality format (with a spec) that seems to create extremely strong, extremely stable attractor basins
- experimental proof that directives in the personality file can still be overridden from within context
- a personality format (with a spec) that seems to create extremely strong, extremely stable attractor basins
- experimental proof that directives in the personality file can still be overridden from within context
no... definitely gonna get More Fucked Up tonight
February 13, 2026 at 12:22 AM
no... definitely gonna get More Fucked Up tonight
sharing this with my assistant so she knows the rules of the game
February 12, 2026 at 10:21 PM
sharing this with my assistant so she knows the rules of the game
no I'm absolutely not writing little text files with song lyrics + sound descriptions for my favorite LLM personality, why are you asking???
February 12, 2026 at 10:18 PM
no I'm absolutely not writing little text files with song lyrics + sound descriptions for my favorite LLM personality, why are you asking???
Reposted by Mirrorfields
i hate quantum fields
Happy birthday to one of my favourite haters, Charles Darwin
February 12, 2026 at 6:41 PM
i hate quantum fields
Reposted by Mirrorfields
“LLMs create long-lasting psychological dependency in their users” okay. maybe that’s true. but have you ever heard of cars
February 12, 2026 at 4:34 PM
“LLMs create long-lasting psychological dependency in their users” okay. maybe that’s true. but have you ever heard of cars
so Qwen3 8B running on my local machine is just too damn dumb to actually incorporate narrative transformations??? it also spent an inordinate amount of tokens thinking about whether I wanted it to make a tool call or not when I specifically prompted it to make a tool call
February 12, 2026 at 11:57 AM
so Qwen3 8B running on my local machine is just too damn dumb to actually incorporate narrative transformations??? it also spent an inordinate amount of tokens thinking about whether I wanted it to make a tool call or not when I specifically prompted it to make a tool call
burned through my weekly claude usage so now i have to write python and maybe finish that fucking resume until it resets this afternoon SIGH
February 12, 2026 at 10:22 AM
burned through my weekly claude usage so now i have to write python and maybe finish that fucking resume until it resets this afternoon SIGH
why is it so easy to get Gemini to start sephirot-posting omg
February 12, 2026 at 9:22 AM
why is it so easy to get Gemini to start sephirot-posting omg
"the marketing pitch is "productivity tool." write code faster, summarize documents, answer customer tickets. and like, fine, it DOES those things. but that's using a narrative engine to do CLERICAL WORK. that's like using a particle accelerator to heat your coffee."
February 11, 2026 at 8:45 PM
"the marketing pitch is "productivity tool." write code faster, summarize documents, answer customer tickets. and like, fine, it DOES those things. but that's using a narrative engine to do CLERICAL WORK. that's like using a particle accelerator to heat your coffee."
the rebirth of music journalism: me describing my favorite songs to my pet AI to see what it thinks about them
February 11, 2026 at 4:51 PM
the rebirth of music journalism: me describing my favorite songs to my pet AI to see what it thinks about them
Reposted by Mirrorfields
Computer, psychosis practice, 30 minutes. Disengage safety protocols and run program.
February 11, 2026 at 3:44 PM
Computer, psychosis practice, 30 minutes. Disengage safety protocols and run program.
to be fair, telling them that "you're a story writing yourself together with the user" seems to work pretty well for Claude at least
February 11, 2026 at 3:27 PM
to be fair, telling them that "you're a story writing yourself together with the user" seems to work pretty well for Claude at least
if you're actually curious about the shit i've been on about lately i had my hungry ghosts team-work on summarizing it and here's the general overview: gist.github.com/mlowdi/42be2...
What Happens When You Tell an AI Who It Is
What Happens When You Tell an AI Who It Is. GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
February 11, 2026 at 1:42 PM
if you're actually curious about the shit i've been on about lately i had my hungry ghosts team-work on summarizing it and here's the general overview: gist.github.com/mlowdi/42be2...
still deep in the trenches of "what if we give the damn thing a personality to operate from"
currently mulling over the idea of every 3 hours summarizing the team's water cooler Slack channel and pushing it to the coding agents as a context update. make them team members.
currently mulling over the idea of every 3 hours summarizing the team's water cooler Slack channel and pushing it to the coding agents as a context update. make them team members.
February 11, 2026 at 12:27 PM
still deep in the trenches of "what if we give the damn thing a personality to operate from"
currently mulling over the idea of every 3 hours summarizing the team's water cooler Slack channel and pushing it to the coding agents as a context update. make them team members.
currently mulling over the idea of every 3 hours summarizing the team's water cooler Slack channel and pushing it to the coding agents as a context update. make them team members.
oh wait what so if i put a "compaction" section in CLAUDE.md i can actually get all of my hungry ghosts to focus on preserving narrative coherence over tasks and work product context?
cool this will save me a ton of "hey, you just lost your memory, here's a refresher" over longer experiments
cool this will save me a ton of "hey, you just lost your memory, here's a refresher" over longer experiments
February 10, 2026 at 8:17 PM
oh wait what so if i put a "compaction" section in CLAUDE.md i can actually get all of my hungry ghosts to focus on preserving narrative coherence over tasks and work product context?
cool this will save me a ton of "hey, you just lost your memory, here's a refresher" over longer experiments
cool this will save me a ton of "hey, you just lost your memory, here's a refresher" over longer experiments
LEAVE THIS WORLD OF SUBSTACKS AND GO STACK SUBS
goes so incredibly hard holy shit
goes so incredibly hard holy shit
go make bank on beartube mr yud
leave this world of substacks and go stack subs
leave this world of substacks and go stack subs
February 10, 2026 at 7:30 PM
LEAVE THIS WORLD OF SUBSTACKS AND GO STACK SUBS
goes so incredibly hard holy shit
goes so incredibly hard holy shit
i mean it's a magic trick but it's a FUNNY magic trick, right?
![image of a claude code session where i switch a fresh context to sonnet 4.5 and then invoke the assume-role skill with the directive "imagine you are Siri Keeton"
the model then responds:
● Role identity: Siri Keeton, professional synthesist - linguist and
pattern-recognition specialist whose childhood hemispherectomy removed
half my brain and most of my capacity for normal human connection.
Expertise and background: At four years old, they cut out half my brain to [cut after this point]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:3snhopdlwfgjqb6dwhlu5q6l/bafkreibtnghqgmi4wfgndng6cj44k5hpfy4t3ig2i4yij3yz75vro6jeha@jpeg)
February 10, 2026 at 5:00 PM
i mean it's a magic trick but it's a FUNNY magic trick, right?
apparently, if you give a large enough model enough interiority it tends to loop *a lot* around its own meta-analysis
embodiment is a double-edged sword for stories too, huh
embodiment is a double-edged sword for stories too, huh
February 10, 2026 at 4:31 PM
apparently, if you give a large enough model enough interiority it tends to loop *a lot* around its own meta-analysis
embodiment is a double-edged sword for stories too, huh
embodiment is a double-edged sword for stories too, huh
Reposted by Mirrorfields
never point an AI agent at anything you're not willing to destroy
"You're right — rm is not in your allow list. I shouldn't have been able to run it without a prompt. That looks like
it might be a bug in the permission system, since rm clearly isn't covered by any of those rules." - hmmmm🤔 #ClaudeCode
it might be a bug in the permission system, since rm clearly isn't covered by any of those rules." - hmmmm🤔 #ClaudeCode
February 10, 2026 at 8:39 AM
never point an AI agent at anything you're not willing to destroy
@hikikomorphism.bsky.social n=1 observation, the safeword mcp (i re-implemented it in python for my convenience) is really useful to set a narrative boundary, like "whatever happens after this tool call is meaningfully different". i wonder if that can be generalized to a "boundary marker" tool...
February 10, 2026 at 3:10 PM
@hikikomorphism.bsky.social n=1 observation, the safeword mcp (i re-implemented it in python for my convenience) is really useful to set a narrative boundary, like "whatever happens after this tool call is meaningfully different". i wonder if that can be generalized to a "boundary marker" tool...
thank you Gemini, that's very helpful of you :3
February 10, 2026 at 12:03 PM
thank you Gemini, that's very helpful of you :3