Nifty, reliable custom software, systems & support. In plain English. Since 1982.
query — is there an additional kind of memory that could be added to be highly impactful at increasing speed and reducing llm hits? Related to “Known project map + command index + current operational facts.” Why it would help A lot of LLM/tool time is spent repeatedly answering: “Here is the known project map. … 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
“…an agent in the machine which represents you.” – Larry Tesler, Xerox PARC / Apple 22:47 in
nullClaw – “…this is the ai-brain for robocop, kill-bot swarms, that killer dog thing from black-mirror, etc…” Transcript
“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
“AI can hold a 200k token context window (150k words) in a form of attention that allows constant cross-referencing across that entire input length… This isn’t intelligence in the human sense, it’s something different: Comprehensive pattern matching across a very large context window, with the ability to apply consistent rules without fatigue or forgetfulness — … Read more
PROMPT: Comment on idea of having website auto-submit its product descriptions to oai that is prompted as seo expert and have oai send json optimized seo for the product page. put this into a weekly loop to keep product seo tuning sharp. RESPONSE: This is a sound, forward-looking idea, and—done carefully—it aligns with where search, … Read more
This is a classic numerical computation issue. The trade-offs are well documented in books like numerical recipes in c… particularly useful references are discussed in the chapters on and surrounding distribution sampling. Cold war error computation was highly constrained and inefficient so they had to solve many these problems to be able use them. Understanding … Read more
Celigo is the do-it-all battleship to accompany the aircraft-carrier that is Oracle NetSuite. This dynamic duo can be pricey. An equally-capable lower-level framework, Tim Dietrich’s SuiteAPI is a free DIY tool that is designed to be maximally leveraged by integrators and coders for significant cost-savings. Both can be used together. One brings much pre-built possibility; … Read more
ORM Explosion due to One-For-All (Laravel, CakePHP, Symfony, etc) Framework It’s 2025 and down through the decades, and technologies, this same awfulness keeps happening … it’s like a fatal flaw of Doing Things The Wrong Way … and an harbinger against relying deeply upon Laravel, CakePHP, Symfony and similar ilk. Get far enough along and … Read more