Author: robert.adlington
-
Scaling Hierarchical Navigable Small World (HNSW) Vector in Redis
if you have different vectors about the same use case split in different instances / keys, you can ask VSIM for the same query vector into all the instances, and add the WITHSCORES option (that returns the cosine distance) and merge the results client-side, and you have magically scaled your hundred of millions of vectors…
-
Notes on American Fascism | The Point Magazine
“What is happening today worldwide,” he writes in “Notes on American Fascism,” “is a reorganization of ancient or new or newish social classes into two social classes: the economically and technologically sophisticated and the failed and unrooted and not sophisticated.” In the essay on Winchell he puts the point more bluntly: “When I was young,…
-
Who is ‘fedora man’? Dapper French teenager in viral Louvre heist photo unmasked | France | The Guardian
“Fedora man”, as users dubbed him, was cast as an old-school detective, an inside man, a Netflix pitch – or not human at all. Many were convinced he was AI-generated. Pedro understood why. “In the photo, I’m dressed more in the 1940s, and we are in 2025,” he said. “There is a contrast.” — Read…
-
Game design is simple, actually – Raph Koster
Some of this is down to personality types, some of it is down to social dynamics, how they were raised, what their local culture is like, what trauma they have had, and countless other psychological things. That’s why one fancy term for this is psychographics. The big thing is, it’s not enough that the problems…
-
ChatGPT Does Not Have Opinions
ChatGPT is not a human, and, unlike teachers & librarians & scholars, ChatGPT does not have a consistent, legible worldview. In my experience, it readily agrees with any premise you hand it — and brings citations. It may have read every article that can be read, but it has no real opinion — so it is not a credible…
-
Aiming for Fullness: The smartphone eradicates “space” in the mind.
The swiping, the news cycles, the screaming, the idiocy — if anything destroys a muse, it’s this. If anything keeps you locked into a fetid loop of looking, looking, and looking once more at the train wreck, it’s this. I find it impossible to feel fullness, even in the slightest, after having spent just a…
-
Interleaved Thinking
Interleaved thinking is essential for LLM agents: it means alternating between explicit reasoning and tool use, while carrying that reasoning forward between steps.This process significantly enhances planning, self‑correction, and reliability in long workflows. — Read on simonwillison.net/2025/Nov/3/minimax/
-
Thinking is not Objective, has a Point of View
The Python developer reads case studies about Go’s performance and their amygdala quietly marks each one as a threat to be neutralized. The Rust advocate looks at identical problems and their Default Mode Network constructs narratives about why “only” Rust can solve them. We’re not lying. We genuinely believe our reasoning is sound. That’s what…
-
MCP as Secure Gateway
Instead of a bloated API, an MCP should be a simple, secure gateway that provides a few powerful, high-level tools: download_raw_data(filters…) take_sensitive_gated_action(args…) execute_code_in_environment_with_state(code…) In this model, MCP’s job isn’t to abstract reality for the agent; its job is to manage the auth, networking, and security boundaries and then get out of the way. This makes…
-
Grokipedia Is the Antithesis of Everything That Makes Wikipedia Good, Useful, and Human
…behind the scenes, there had been robust conversation and debate by Wikipedia editors as to exactly what constitutes an “unusual” death, and that several previously listed “unusual” deaths had been deleted from the list for not being weird enough. For example: People who had been speared to death with beach umbrellas are “no longer an…