Project Turaco Is Finally Showing Promise
For 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? Tha
fotiecodes - AI/ML/Software Engineer
Latest articles
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 ...
How i passed my Google Cloud Certifications (and what I learned from failure): Plus study tips
I 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 ...
I was wrong: Small is the new big for local AI agents
TL;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...
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...
Precise AI Photo Edits: The Red‑Box Trick With Gemini’s Nano Banana Model
Last 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...
VibeVoice 1.5B: Four Distinct Voices, 90 Minutes and a Leap Forward for Text‑to‑Speech
An open-source text-to-speech model built for long-form, multi-speaker dialogue.