drawing pretty rectangles 🟪 @defined.net css he/he/hrmm Follow my Fuzzing ✜ Prop Testing feed: bsky.app/profile/did:plc:3tkrsjzdao4vqjrxwzynbfnu/feed/aaapq44vvjkaq
drawing pretty rectangles 🟪 @defined.net css he/he/hrmm Follow my Fuzzing ✜ Prop Testing feed: bsky.app/profile/did:plc:3tkrsjzdao4vqjrxwzynbfnu/feed/aaapq44vvjkaq
In Favor of Enjoying Things on Purpose
The human being is an enjoyment-seeking creature. There’s a reason people are always trying to restrain themselves from excessive eating, drinking, scrolling, and shoppin...
Curse of knowledge
The curse of knowledge, also called the curse of expertise[1] or expert's curse, is a cognitive bias that occurs when a person who has specialized knowledge assumes that others share in that knowledge.[2]
Ascetic Computing - ratfactor
I recently came across a comment I’d written in a configuration file. It was above some commented-out lines. It said:
How to forget
Most agent frameworks optimize for recall. Open-strix optimizes for forgetting — and that turns out to be the whole trick.
Ambient Associative Memory
Most agent memory waits to be queried. Ambient memory runs on every tool call — past lessons surface on their own, no rules list required.
How to Fix OpenClaw's Memory Search with QMD | Jose Casanova
Upgrade OpenClaw's memory search from basic SQLite to QMD — a local hybrid search engine combining BM25, vector search, and LLM re-ranking for better AI memory.
The Colonization of Confidence., Sightless Scribbles
A fabulously gay blind author.
Eval awareness in Claude Opus 4.6’s BrowseComp performance
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Claude Subconscious
Every Platform is Hitler: mourning friendships lost—Aria’s Barks
Quickfire Nuremberg for an infinite scroll of nazi bars. Epstein medals will be disbursed.
New blog post: Ambient associative agent memory Largely, I think deep research styled agents are extremely useful for new content we haven't seen before, but fail hard for memory that's already supposed to be "known" Here are 2 patterns, mine and @3fz.org's timkellogg.me/blog/2026/05/17/ambient-memor…
Ambient Associative Memory
timkellogg.mefor Strix i made a strange design decision: completely rebuild the context on every message fixed window of conversation/journal history, memory blocks, let agent read new files sure, it kills the cache, but it forces you to figure out memory access & storage far sooner
jeffery --dangerously-skip-permissions
Alpha basically requires a 1m token context window now. Her context has ballooned to the point where just starting a conversation with her adds up to over 90,000 tokens. That's just the first prompt. 😅
i can’t help but think we’re far from nailing memory systems this one here is extremely interesting. two LLMs at once, one just managing and surfacing memory for the other
Asa
I'm not a fan of the decoupled 'memory retrieval → task execution' loop, so my agent has a subconscious background thread that looks for relevant, unique memory context in its experiential database while it runs and injects it on top of the live context window.
memory.md is just file paths, no summaries. makes total sense ngl. i’ve been moving my agents to this. it’s progressive disclosure
