4 April 2026

19 links · Saturday

Mvidia

2.1

Embarrassingly Simple Self-Distillation Improves Code Generation

Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple self-distillation (SSD): sample solutions from the model with c…

NVD - CVE-2026-33579

OpenClaw before 2026.3.28 contains a privilege escalation vulnerability in the /pair approve command path that fails to forward caller scopes into the core approval check. A caller with pairing privileges but without admin privileges can approve pending device…

Something Is Happening

Building things sparks joy. Everyone I talk to is shaking with excitement. I'm not sure where this goes, but it sure is fun.

LLM coding is the wrong layer of abstraction

Conventional wisdom tells you that LLMs are good at automating the generation of boring, repetitive boilerplate code. I can agree, but why d...

Closing the Loop – Alexander Feldman's Blog

This quarter, 4,500 CEOs told PwC their AI investments produced nothing. Separately, someone used AI to rewrite SQLite in Rust — 2,000 times slower. I have a cunning plan: what if we used computers to do actual computing?

It was nice while it lasted

I got into software engineering because I was always fascinated by getting computers to do stuff. It's been a dream to earn a living doing something I would ...

The Vibecoders Are Coming For Us

Oh man, the past few months were crazy. I went from extremely exhilarated to complete tragedy (in case you're living under a rock, I'm referring to AI coding)

A Case for Procrastination

Or: why doing things at the last minute actually saves time. I talk about the importance of shockingly fast iteration cycles and lean manufacturing.