#jose = josekit, biscuit, jose-jwk, jwk-simple, picky, aliri, json-proof-token, ssi-vc-jose-cose, reallyme-jose-proto, jose-b64, etc.
Home Getting Started Concepts Reference Wire Protocols (BI Tools) dbt Tutorials Notebook Auto-Ingestion Notebook Time Dimensions Notebook Joins Notebook Joined Measures Notebook Multistage Queries Notebook Aggregations Notebook Lightning Talk Notebook What is a semantic layer anyway? Why not just ask Claude? Why just asking your agent to generate SQL is not optimal The other half: business context To enable reliable analytics, an agent needs BOTH kinds in one context provider What an agent needs to actually
Python is not the most suitable for Data Engineering. Let's explore why Rust has potential, what it does well and why it has become the most loved programming language for a while.
An exploration of Rust as a language for full-size web apps, as well as web-focused Crates
# 447 The Exclusion Brouhaha In 1680 and 1681, Shaftesbury led an increasingly shrill and effective campaign, asppeling to popular opinion to force Charles into calling a new parliament. There he could be forced to learn about the power of the exlusionist movement which could be brought to bear. But Charles would learn a different lesson, and at Oxford in 1681, would start his own campaign. Download Podcast - 447 The Exclusion Brouhaha (Right Click and select Save Link As) Transcript Now then, last time
Rust FAQ has 1653 in-depth articles answering technical questions with code examples, decision matrices, and practical advice — written for engineers who need real answers, fast.
Write to markdown files. Put it in your governed database. Both instincts are right that memory must be governed, and both stop short of the operations a memory layer adds. Where build-it-yourself breaks.
Benjamin Anderson Blog About CV Projects Blog Contra DSPy and GEPA Workflows are out. Agents are in. Posted Dec 17, 2025 by Benjamin Anderson I have something shameful to confess—I have been holding hate in my heart. It pains me to say this, because the folks behind it are brilliant, kind, and thoughtful people, and deserve nothing but love and appreciation. Nevertheless, I must share my authentic truth: I hate DSPy and GEPA to the core of my being. I tried to like them. I really did. I went through the 45-
Posts about databases written by way0utwest
14 models, 4 arms, ~3400 API calls. No model balanced false-accept and recall with pattern strings. With real file snippets: recall 0.08→0.88 at FA=0.02. The problem was the evidence, not the model. Tagged with llm, memorylayer, agents, benchmark.