Project Turaco Is Finally Showing PromiseFor more than a year, I have been trying to answer one question: can we build a machine translation model that translates English into natural Cameroon Pidgin without sounding like it is guessing? ThaSep 23, 2026·3 min read·9
Google Just Dropped Transformer 2.0: Meet "Nested Learning"I’m sitting here with a hot cup of coffee, about halfway through Google’s new paper on "Nested Learning," and I have to be honest: I need to get this out of my head and onto the screen. Usually, when a big lab drops a paper, I skim the abstract, nod ...Dec 16, 2025·5 min read·3.1K
How i passed my Google Cloud Certifications (and what I learned from failure): Plus study tipsI recently achieved something I’m pretty proud of: I passed both the Associate Cloud Engineer (ACE) and the Google Cloud Professional Data Engineer (PDE) certification exams. It feels good to say that now, but I want to be real with you, it wasn’t a ...Dec 5, 2025·5 min read·114
I was wrong: Small is the new big for local AI agentsTL;DR: We’ve been obsessed with parameter counts for too long but running massive models locally is a pain. The real unlock isn't a smarter God-model; it's a swarm of small, specialized agents running locally. My M1 Mac is suddenly a powerhouse. Comb...Nov 24, 2025·4 min read·360
Gemini 3 is a monster.I opened X (formerly twitter) today and saw my timeline melting down. Everywhere I looked, people were talking about gemini-3.0. Someone said "It's over.", I saw screenshots of benchmarks that looked impossible. Naturally, I was skeptical. We see hyp...Nov 19, 2025·5 min read·1.3K
Precise AI Photo Edits: The Red‑Box Trick With Gemini’s Nano Banana ModelLast weekend, I spent a sunny and very hot afternoon in Lisbon(so glad summer is almost over) playing with Gemini’s Nano Banana, Google’s latest image‑editing model. When I first tried to tweak a photo, I did what most of us do: type a prompt, hit ge...Sep 23, 2025·5 min read·520
VibeVoice 1.5B: Four Distinct Voices, 90 Minutes and a Leap Forward for Text‑to‑SpeechAn open-source text-to-speech model built for long-form, multi-speaker dialogue.Aug 27, 2025·7 min read·276
