Nifty, reliable custom software, systems & support. In plain English. Since 1982.
It is said that AI is only: ‘based upon your “training” (which is: discerning token-interconnection likelihood), show what is the next most likely token?’ That is by definition recall. If you “trained” AI solely on the single token “ai is ai” then its answer could only ever be “is” or “ai” or “is ai” or … Read more
SOURCE: https://www.lennysnewsletter.com/p/how-to-turn-your-ai-into-a-world AI models are capable of amazing creativity, but that creativity gets stifled by how they’re trained. Large language models are next-token predictors: at each step, they look at a sequence of text and predict what comes next based on millions of examples. The results may be rated by humans, and those ratings fed … Read more
write a book for me, chapter at a time. its called SECONDEVE and it’s about a girl who was cloned 8 months prior to birth; evey and eve were ‘born’ one month apart, their senses are intermingled, their toughts interwoven. Each completes the other’s sentences, ideas, responses. It’s uncanny. This could seemingly wreck their lives … Read more
They are just gigantic probability calculators. Everyone who thinks LLMs are sentient should be forced to watch this.
Rather than merely predicting ‘what word most often comes next’, conjoined alternate “world views” are surmised to offer ‘the next levels’ in machine learning, making our tools more anthropomorphic and adept at ‘real-world’ use. Imagine that Japanese- and Kanji-trained models that have also been trained with ‘Samurai moves’ and culturally-specific videos would be ‘tuned’ to … Read more
Multi-Memory Harness Technique for AI LLM CLI (codex, opencode, pi, etc) PRIMARY CLAIM — Memory retrieval reduced repeated context reconstruction and likely reduced downstream LLM reasoning/search work. Two Kinds of Mem 2 kinds of ‘long-term memory’, 2 strengths, 2 uses/reasons 1 Postgres PGVECTOR 2 WIKI How the memories are best used › posit: pgv stores … Read more
700-word Executive Summary below AI adding to / morphing from, not replacing SEO.AI uses SEO to choose authority, truth, data-source.1 SEO defines the verifiable truth/data.2 GEO makes truth/data understandable to “AI” (LLM/RAG).3 AIO facilitates business (sales, links, lookups) via AI.—I asked AI: Regarding seo and ai — is the above accurate, concise? —- It replied: … Read more
When a model trains, it is not “learning facts” the way a human does. It is adjusting billions of numbers so that: Given this sequence of tokens, what token is most likely next? That’s it. No concepts. No understanding. Just probability shaping. But here’s the magic: When trained on enough text — books, code, discussions, … Read more
“Your brain was never designed to be a storage system. It was designed to think. Every time you force it to remember something instead of letting it work on something new, you’re paying a tax you don’t see. And in 2026, when AI can multiply what you produce, that tax is more expensive than ever.” … Read more
It’s been recently promulgated that the majority of website traffic, in general, is by bots, crawls, ai-agents, etc — making the web more computer-to-computer rather than human-to-computer based. Bots as the Majority of Web Traffic? Evidence, Measurement Pitfalls, and a Bot‑First Playbook Executive synthesis on the 51% claim Multiple credible, primary sources now support the … Read more