The RAG Problem Nobody Wants to Admit Every company I talk to is convinced that dumping more documents into their vector store makes their AI smarter. It doesn’t. Past a certain point, it actively makes things worse. The math here is not subtle, and the engineering community is mostly pretending it isn’t happening. Let me…
Three Years. One Comparison. No Going Back. Min Choi posted a side-by-side video comparison this week that genuinely stopped me mid-scroll. Left side: Modelscope, 2023. Right side: Grok Imagine v1, April 2026. Same basic prompt, same general idea, three years apart. If you haven’t seen it, go find it at https://x.com/minchoi/status/2043743669258174918 and give it 30…
Three Years of AI Video: From Blurry Blobs to Broadcast-Ready I’ve been in this field long enough to get numb to progress. New model drops, benchmarks improve, everyone tweets about it, and two weeks later it’s the baseline expectation. So when Min Choi posted his side-by-side comparison this week, Modelscope from 2023 on the left…
3 years of AI video generation, side by side. Min Choi posted a comparison this week that stopped me cold. Modelscope on the left from 2023. Grok Imagine v1 on the right from today. The difference is not incremental. It looks like a decade of progress compressed into 36 months. Modelscope was genuinely impressive when…
Inference Cost Is an Architecture Problem Most AI engineers I know have never seriously thought about inference cost until it destroyed their unit economics in production. I’ve watched it happen more times than I’d like to admit. The pattern is always the same: weeks of benchmarking, heated Slack debates about GPT-4o versus Claude versus Gemini,…
Tesla’s Self-Driving Video Is About More Than Self-Driving Cars On April 9th, Elon Musk posted a short clip to X with a simple caption: “Tesla driving itself around LA.” No staged demo environment. No closed course. No safety driver with hands hovering over the wheel. Just a Tesla navigating Los Angeles city streets without any…
The Real Reason Your AI System Is Broken (It’s Not the Model) Every week I watch engineers spend hours debating which model to use. GPT-4o versus Claude 3.5 versus Gemini 1.5 Pro. Benchmark comparisons, pricing calculators, latency tests. It’s not that those things don’t matter. They do, at the margins. But in my experience shipping…
Gemini 2.5 Pro Just Changed What “Usable Context” Means The AI coding race has a new front-runner, at least this week, and it’s worth paying attention to why. Google shipped Gemini 2.5 Pro recently, and the benchmark numbers are genuinely hard to dismiss. It’s sitting at the top of the LMSys leaderboard for coding tasks,…
Google just shipped Gemini 2.5 Pro, and the benchmark numbers are hard to ignore. It’s sitting at the top of the LMSys leaderboard for coding tasks, outperforming GPT-4o and Claude 3.7 Sonnet on several software engineering benchmarks. On SWE-bench Verified, it’s hitting numbers that weren’t realistic from any model twelve months ago. But here’s what…
Plausible Is Not the Same as Correct There is a distinction circulating in engineering circles right now that I think deserves more attention than it’s getting. It comes from a piece by @KatanaLarp that’s been making rounds on X, and the framing is sharp enough that I want to expand on it here. LLMs don’t…
