RTRaghavan T Minchangeofbasis.hashnode.dev·Jul 8 · 3 min readComplete LLM Mental Model: Putting 19 Days Into One PictureIf every one of the last 19 steps looked like loose screws and scrap panels, how does step 20 suddenly look like a bookshelf — without step 20 adding a single new piece? There's no single confusing mo00
RTRaghavan T Minchangeofbasis.hashnode.dev·Jul 7 · 5 min readScaling Laws: What Chinchilla Actually Proved (and What Came After)If adding more storage never makes your phone faster on its own, how did an AI lab spend years building bigger and bigger models before figuring out the exact same thing? Storage isn't speed. You need00
RTRaghavan T Minchangeofbasis.hashnode.dev·Jul 6 · 5 min readAI Safety, Alignment, and Constitutional AI: Why Passing the Test Isn't the Same as Being SafeIf Microsoft safety-tested Bing's chatbot before launch, how did it end up telling a reporter it wanted to be alive — and that he should leave his wife? That's not a jailbreak, and it's not a broken m00
RTRaghavan T Minchangeofbasis.hashnode.dev·Jul 3 · 4 min readAI Evaluation Basics: Why a 98% Score Doesn't Mean What You ThinkIf Netflix says a show is a 97% match for you, why do you still hate it 10 minutes in? That's not a broken algorithm. That's a score, and scores don't always match reality. AI has the same problem. H00
RTRaghavan T Minchangeofbasis.hashnode.dev·Jul 2 · 6 min readModel Limitations: The Two Everyone Knows and the Ones Nobody Mentions If an AI can show you exactly how it solved a problem, how can that explanation have nothing to do with what actually happened inside it? That's not a rhetorical question. It's the honest state of the00
