PinnedJulian BBehind each LLM inference event..Is a datacentre and industry on fire 🔥(with demand)Jul 11Jul 11
Julian BShaking the Graph DB decision treeA whirlwind look at latest features & relative cost; “Spanner Graph” Vs Neo4j Aura vs AWS NeptuneAug 25Aug 25
Julian BML: Time to reconsider Poetry?Speed and flexible factoring. UV calls time on Poetry’s dawdlingAug 23Aug 23
Julian BEpisode IV: A new hope for HLD kindExamples, solutions & graphs. Part four of a seriesAug 14Aug 14
Julian BSmash the HLD Hegemony, starting with YEmbrace ‘Y’ Statement Simplicity and AI-Power Design DecisionsAug 14Aug 14
Julian BLLM cost reduction OlympicsGold goes to Google with Gemini Flash 1.5; Slashing inference prices by 80%Aug 9Aug 9
Julian BInference cost OlympicsIs time (waiting) an equally effective LLM cost optimisation strategyAug 9Aug 9
Julian BBuilding the stairway from HLD hellSix LLM process innovations on ‘Y’ statement ADr’sJul 31Jul 31
Julian BRecap: Sovereign AI growth ahead.AI plan driver appointed; “AI Infrastructure and Compute” featured.Jul 29Jul 29
Julian BLiar! Can you trust that Bot. How do we measure what matters?A toolbox analogy on evaluations …..(& a talk for A level students on AI engineering)Jul 20Jul 20