Zero PPP knowledge to a submitted driver patch, in about an hour
They pasted raw PPP frames in hex into Gemini, which decoded and explained every byte. An hour later they knew enough to fix a Zephyr OS driver bug and submit a patch.
Done withGeminiSpotted· by HN user olalonde· Oct 15, 2026
Result Every byte decoded and explained
“In about an hour, I knew enough about PPP to fix the bug and submit a patch.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Pasted logs of raw PPP frames in hex into Gemini, which decoded everything and explained what each byte meant, while they worked on a bug in a PPP driver for Zephyr OS.
How it went
In about an hour they knew enough about PPP to fix the bug and submit a patch.
Try it yourself with Gemini
I'm debugging [protocol] in [project]. Here are raw frames from the log in hex: [paste]. Decode each frame field by field, explain what each byte means and what the exchange is trying to do, and point out anything that doesn't follow the spec. Then help me find where in this code [paste] the behaviour goes wrong.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Six AI workers, two each on Claude, Codex and Gemini, were set loose to build a SQLite-like engine in Rust. It passed 64 queries of a 1,000+ query suite, with slop like redundant buffer copies and no concurrency.
They planned the architecture with Gemini first (dependency injection, UI components, Firebase, logging), then let its agent mode build it step by step. The app works like a charm.
The malware was cleaned out, but a hidden backup in the database, triggered by the WordPress cron, would have brought it back. Gemini pulled the encrypted packages apart and spotted it.
They'd written one by hand years before, so they knew exactly what they wanted. In VS Code's Agent Mode, Gemini built it and refactored it into a Python decorator. One dumb corner case slipped through.
It started as a hand-drawn layout for primes by a graphic designer. Gemini and ChatGPT turned it into C++, and the ~3.1x speedup came from cache use, not new math.
Never built for mobile, a parent of three, a busy life. Gemini guided the Kotlin architecture and the UI, and their first Android app was a real joy to build. Impossible a couple of years ago, they say.