Sean Goedecke

Sean Goedecke

Archives
Log in
Subscribe
November 2, 2026

This week on seangoedecke.com

Here's what I wrote this week. If you'd rather get each post as it comes out, switch here.

Reliably aligning LLMs is impossible in principle

Powerful AI is unpredictable. Your robotic butler may suddenly decide to kill you1 for no comprehensible reason, in the same way that Bing’s helpful chat AI would sometimes try to blackmail or seduce its users. “Solving alignment” means understanding even superintelligent AI minds well enough to be confident they’ll never do that. As I see it, solving alignment for LLMs isn’t just impossible, it’s incoherent: we can’t even articulate what it would look like to succeed.

LLMs are not blind optimizers

Prior to LLMs, AI safety researchers thought AI would be a “blind optimizer”: like a chess engine, it would be superhumanly focused on achieving some fixed goal. If the goal wasn’t safe (for instance, “manufacture cheap …

Read the rest on seangoedecke.com →

Fast and slow ways to improve your reputation

To get a good reputation in tech companies, you need to work on important projects. However, you need a good reputation first in order to get assigned important projects. Doesn’t that make it impossible to get started? I get a lot of emails from engineers who are struggling with this problem. They go like this:

I work with a strong senior engineer. I feel like my manager structures work so that strong engineer always gets the visible work, and the more they do, the more opportunities they get, while I sit on the sidelines. My manager agrees with me that it’s time for me to start leading work myself, but every time a new project appears it always …

Read the rest on seangoedecke.com →

Don't miss what's next. Subscribe to Sean Goedecke:
← Newer Audience capture Older → Reliably aligning LLMs is impossible in principle
Share this email:
Share on LinkedIn
GitHub
LinkedIn
Powered by Buttondown, the easiest way to start and grow your newsletter.