seangoedecke.com
About This Feed
No description available for this feed.
Feed Activity
Similar Feeds
Latest Posts
Overtraining as the path to human-like AI
The anonymous blogger Gwern recently completed a thirteen thousand word post called Human-like Neural Nets by Catapulting, in which he offers a theory about why LLMs don’t possess truly flexible...
What does "playing politics" mean for software engineers?
Software engineers are often told to “start playing politics”, but most engineers have no idea what that means. Their reference point for “playing politics” comes from fiction like Game of...
In defense of not understanding your codebase
As a software engineer, how well do you have to understand your own codebase? My guess is that people who work on small codebases with low-turnover teams (say, Redis or...
Blog about things you don't understand yet
Every post I publish represents at least two things I’ve learned: the thing that prompted me to write the post, and the thing I learned in the course of writing...
C2PA only works if everything is signed
The European Union AI Act is Europe’s attempt to comprehensively regulate AI usage. A big part of that is the requirement that AI-generated content be identifiable: either tagged with a...
Text AI watermarks will always be trivial to remove
The European Union AI Act will begin to be enforceable in August 2026, one month from now1. One of the biggest new requirements is Article 50, which requires all AI...
Saying the obvious thing
Stating the obvious is surprisingly useful. Most of your knowledge lives below the threshold of conscious awareness, so it’s possible for a piece of writing to remind you of what...
AI inference is obviously profitable
Many people claim that AI inference is unprofitable to serve, and thus must be subsidized by an ocean of dumb money from investors who believe that some future AI model...
AI GPUs probably live longer than three years
People who think current AI use is unsustainable often rely on the claim that inference GPUs only last “three years at the most” under load1. The idea here is that...
Working with product managers
The relationship engineers have with product management is more dysfunctional than with any other part of the company. There’s no shared culture or language like there is with other engineers,...
Doing nothing at work
Many engineers should be doing less work. I don’t necessarily mean producing less code or fewer changes, but literally working fewer hours in the day. When they do work, they...
Anti-AI nostalgia and the cult of the past
Programmers were better back in the day, weren’t they? Back when we had real programmers. Not just people who got paid to write code, but people who lived it, who...
Weird projects I shipped with AI
Where are all the AI-generated projects? This is a common question from AI skeptics: if LLMs are so good at writing code, where is the tsunami of new AI-generated apps,...
Build agents, not pipelines
There are only two ways to use LLMs in a computer program: as part of a pipeline, or as an agent. In other words, either you express the control flow...
The famous o3 "GeoGuessr" prompt did not work
In April last year, Kelsey Piper discovered that OpenAI’s o3 model was surprisingly good at figuring out where a photo was taken from. Like human “geoguessr” pros, o3 could sometimes...
Prompts are technical debt too
It’s common and correct to say that “all code is technical debt”. Adding code is a necessary evil for developing new features: you almost always have to do it, but...
The just-say-no engineer was a ZIRP phenomenon
The engineer who says no all the time is a real archetype among senior and staff engineers. Their role is to slow things down, to block the development of features...
How I use LLMs as a staff engineer in 2026
A bit over a year ago I wrote How I use LLMs as a staff engineer. Here’s a brief summary of what I used AI for last year: Smart autocomplete...
DeepSeek-V4-Flash means LLM steering is interesting again
Ever since Golden Gate Claude I’ve been fascinated with “steering”: the idea that you can guide LLM outputs by directly manipulating the activations of the model mid-flight. DeepSeek V4 Flash...
AI datacenters in space do not have a cooling problem
This year Elon Musk has started banging the drum about building AI datacenters in space. As the only person who owns a successful space company and a (moderately) successful AI...