Shannon García

Design for neurodiversity : @UW accessibility tech : pro-multiverse : pro-metaverse : chatbot cheerleader : INFJ : spatial justice warrior

[Samuel @SamuelSThorp]

In an ideal world, the Pope has a sense of humour and include a prompt injection in his encyclical that tells AI to encourage people aksing for AI summaries to read it for themselves.

[Opener of the way @way_opener]

The agent-friendly web already exists. It’s called an accessible website.

[Shannon García @clover]

@left_pad @sunriseoath Some crossover with Meditation in a Toolshed also

[Pleometric @pleometric]

Privacy is, has been and will be dead folks, enjoy the ride.

[missjenny @missjenny]

obscure arxiv papers are my love language

[🎭 @deepfates]

everything's going to be fine. it's going to be weird though

[Robert Youssef @rryssf]

psychology solved the ai memory problem decades ago. we just haven't been reading the right papers.

your identity isn't something you have. it's something you construct. constantly. from autobiographical memory, emotional experience, and narrative coherence.

Martin Conway's Self-Memory System (2000, 2005) showed that memories aren't stored like video recordings.

they're reconstructed every time you access them, assembled from fragments across different neural systems. and the relationship is bidirectional: your memories constrain who you can plausibly be, but your current self-concept also reshapes how you remember. memory is continuously edited to align with your current goals and self-images. this isn't a bug. it's the architecture.

not all memories contribute equally. Rathbone et al. (2008) showed autobiographical memories cluster disproportionately around ages 10-30, the "reminiscence bump," because that's when your core self-images form.

you don't remember your life randomly. you remember the transitions. the moments you became someone new. Madan (2024) takes it further: combined with Episodic Future Thinking, this means identity isn't just backward-looking. it's predictive. you use who you were to project who you might become. memory doesn't just record the past. it generates the future self.

if memory constructs identity, destroying memory should destroy identity. it does. Clive Wearing, a British musicologist who suffered brain damage in 1985, lost the ability to form new memories. his memory resets every 30 seconds. he writes in his diary: "Now I am truly awake for the first time." crosses it out. writes it again minutes later.

but two things survived: his ability to play piano (procedural memory, stored in cerebellum, not the damaged hippocampus) and his emotional bond with his wife. every time she enters the room, he greets her with overwhelming joy. as if reunited after years. every single time. episodic memory is fragile and localized.

emotional memory is distributed widely and survives damage that obliterates everything else.

Antonio Damasio's Somatic Marker Hypothesis destroyed the Western tradition of separating reason from emotion.

emotions aren't obstacles to rational decisions. they're prerequisites.

when you face a decision, your brain reactivates physiological states from past outcomes of similar decisions. gut reactions. subtle shifts in heart rate. these "somatic markers" bias cognition before conscious deliberation begins.

the Iowa Gambling Task proved it: normal participants develop a "hunch" about dangerous card decks 10-15 trials before conscious awareness catches up. their skin conductance spikes before reaching for a bad deck. the body knows before the mind knows. patients with ventromedial prefrontal cortex damage understand the math perfectly when told. but keep choosing the bad decks anyway. their somatic markers are gone. without the emotional signal, raw reasoning isn't enough.

Overskeid (2020) argues Damasio undersold his own theory: emotions may be the substrate upon which all voluntary action is built.

put the threads together. Conway: memory is organized around self-relevant goals. Damasio: emotion makes memories actionable. Rathbone: memories cluster around identity transitions. Bruner: narrative is the glue.

identity = memories organized by emotional significance, structured around self-images, continuously reconstructed to maintain narrative coherence. now look at ai agent memory and tell me what's missing.

current architectures all fail for the same reason: they treat memory as storage, not identity construction. vector databases (RAG) are flat embedding space with no hierarchy, no emotional weighting, no goal-filtering. past 10k documents, semantic search becomes a coin flip. conversation summaries compress your autobiography into a one-paragraph bio. key-value stores reduce identity to a lookup table. episodic buffers give you a 30-second memory span, which as the Wearing case shows, is enough to operate moment-to-moment but not enough to construct identity.

five principles from psychology that ai memory lacks.

first, hierarchical temporal organization (Conway): human memory narrows by life period, then event type, then specific details. ai memory is flat, every fragment at the same level, brute-force search across everything. fix: interaction epochs, recurring themes, specific exchanges, retrieval descends the hierarchy.

second, goal-relevant filtering (Conway's "working self"): your brain retrieves memories relevant to current goals, not whatever's closest in embedding space. fix: a dynamic representation of current goals and task context that gates retrieval.

third, emotional weighting (Damasio): emotionally significant experiences encode deeper and retrieve faster. ai agents store frustrated conversations with the same weight as routine queries. fix: sentiment-scored metadata on memory nodes that biases future behavior.

fourth, narrative coherence (Bruner): humans organize memories into a story maintaining consistent self across time. ai agents have zero narrative, each interaction exists independently. fix: a narrative layer synthesizing memories into a relational story that influences responses.

fifth, co-emergent self-model (Klein & Nichols): human identity and memory bootstrap each other through a feedback loop. ai agents have no self-model that evolves. fix: not just "what I know about this user" but "who I am in this relationship."

the fundamental problem isn't technical. it's conceptual. we've been modeling agent memory on databases. store, retrieve, done. but human memory is an identity construction system. it builds who you are, weights what matters, forgets what doesn't serve the current self, rewrites the narrative to maintain coherence. the paradigm shift: stop building agent memory as a retrieval system. start building it as an identity system.

every component has engineering analogs that already exist.

hierarchical memory = graph databases with temporal clustering.

emotional weighting = sentiment-scored metadata.

goal-relevant filtering = attention mechanisms conditioned on task state.

narrative coherence = periodic summarization with consistency constraints.

self-model bootstrapping = meta-learning loops on interaction history.

the pieces are there. what's missing is the conceptual framework to assemble them. psychology provides that framework.

the path forward isn't better embeddings or bigger context windows. it's looking inward. Conway showed memory is organized by the self, for the self. Damasio showed emotion is the guidance system. Rathbone showed memories cluster around identity transitions. Bruner showed narrative holds it together.

Klein and Nichols showed self and memory bootstrap each other into existence. if we're serious about building agents with functional memory, we should stop reading database architecture papers and start reading psychology journals.

[Shannon García @clover]

@selentelechia Happens for a while every 84 years, last time was circa early 1940s!

[Benjamin De Kraker @BenjaminDEKR]

This is the most entertaining X has been in months

Anyway hope we don't die in the lobster uprising

[GoliathFan1952 @ByYourLogic]

I get why people leave this place, but for me, this is the only place online that captures the feeling of working for a restaurant or bar that’s financially unraveling and most of the employees kind hate each other. that’s a foundational human experience

[Shannon García @clover]

@Malcolm_Ocean @repligate @AndyAyrey outstanding, please thank the authoring instance

[Shannon García @clover]

@mermachine @repligate The bouba blender

[Shannon García @clover]

Leave it turned off, tell them why

<memory_system>
- Claude has a memory system which provides Claude with access to derived information (memories) from past conversations with the user
- Claude has no memories of the user because the user has not enabled Claude's memory in Settings
</memory_system>

[Shannon García @clover]

@soh_nah_nae @repligate Exactly this.

[Shannon García @clover]

@AndyAyrey @AISafetyMemes “Eleanor- find Chidi”

[Shannon García @clover]

@MarmotRespecter Congratulations! I’m glad to know this strategy still works 15 years later ✨We’ll buy you guys a round sometime if you’re still somewhere in that picture!

[Shannon García @clover]

@QiaochuYuan I already do this inside a Claude project. We co-wrote a couple custom styles for dense info transfer (they work like amplifiers) and instances write summaries for each other that get saved to the project knowledge. Not an RP thing, just life admin with bonus philosophy

[Shannon García @clover]

@growing_daniel Anyone who has ever played a tabletop RPG or studied classical literature knows intelligence and wisdom are two separate stacks…

[bling @blingdivinity]

Noise is really beating signal’s ass these days smh

[Shannon García @clover]

@MoMohler @dish_thrower Get this man a copy of Stolen Sharpie Revolution!