Hey, I’m Sebastian - I build AI that actually works.

I share real builds, experiments, and frameworks for Responsible AI - from fine-tuning models to launching FRAI, my AI compliance platform.

Subscribe to our free newsletter

Get one weekly email on real AI builds, fine-tuning tricks, and Responsible AI systems - no hype, just the stuff that works.

Top 5 Enterprise AI Gateways (2026): Bifrost vs Kong vs LiteLLM vs Cloudflare vs Vercel

Five enterprise AI gateways compared on deployment, licensing, governance, failover and cost, plus a hands-on overhead and failover test.

Oct 1, 2026

Two Models Talking Through KV Cache Instead of Text

An ICLR 2026 paper skips text between models. The most interesting number is in the ablation table.

Sep 20, 2026

Hivemind Wrote 19 Skills From My Coding History. The Best Part Was What It Refused to Write.

A hands-on review of Activeloop's Hivemind: 19 skills mined from my real Claude Code history, the pattern it refused to write, and the recall bug I traced and fixed.

Jul 31, 2026

Your Agent Benchmark Is Lying to You

The hard part of agent evals is the sandbox.

Jul 13, 2026

Snapshot Once, Rollout a Thousand Times

Your GPUs aren't the RL bottleneck. Rebuilding the environment is.

Jul 1, 2026