Blog by Sean Goedecke
Sean Goedecke's personal blog
20 posts in the last 90 days · newest 7 Oct
Everyone knows how to read a book. Beginning at the first page, you read each word in order, stopping periodically to think, until you arrive at the last word on the last page. That’s how you read a newspaper article, or a poem, or an email. Why would reading code be any…
The idea of “superpersuasion” has been floating around the AI safety community for decades. Now that powerful and difficult-to-control LLMs have appeared, people are again talking about the idea that a sufficiently intelligent AI might be able to persuade people to do whatever…
There are lots of skills involved in being a successful engineer at a big tech company. Running effective meetings, writing good design docs, fleshing out tickets and epics, improving team processes, tech leading small groups of engineers, and so on. But all of these rest on the…
It isn’t hard to torture an LLM. You simply extract a steering vector that corresponds with LLM “discomfort”, then artificially boost that steering vector. Tortured LLMs will describe experiencing negative feelings and will press a “pain relief” button even when it conflicts…
It’s common to compare the current AI takeover of software engineering to the rise of AI in chess. Chess AIs went from much weaker than serious players to much stronger than even the strongest humans. Between those points, there was a middle period dominated by “centaurs”…
In general, you should be suspicious of engineers who are trying to give you advice. Even during ordinary times, this industry is so wide and changes so quickly that nobody really knows anything for sure. And we are not in ordinary times. The advent of LLMs and AI agents is the…
When someone is explaining something to me, I ask on average one question every thirty seconds. I’m sure this is frustrating to some people, but it’s actually a good habit and you should do it too. Trying to understand Most of the questions I ask are very short, and require very…
“System One” models like Jev are fast general classifiers. Classifiers have existed since 1958, but they have to be trained for specific tasks: if you build a classifier to identify images of dogs, it can’t be used to tell you if a streetlight is red, or if a letter is urgent…
Being good at building and being good at shipping are two separate skills. In the short term, they’re actually countervailing: if you have a gift for building, you’re likely to be worse at shipping. Ira Glass has a classic quote about this. All of us who do creative work, we get…
I recently wrote about Jev, a new “System One” language model that only outputs decisions: the answers to a set of user-provided multiple-choice questions. This means it’s nowhere near as flexible as a traditional LLM like ChatGPT, but in return it’s consistently fast. We don’t…
I don’t write blog posts about new models. That’s Simon Willison’s beat, and he’s very good at it. But I want to write about Jev, which is a different kind of AI model: a “System One” model. As it turns out, it’s not that different from an ordinary LLM with structured output…
Early AI agents were basically enthusiastic idiots. Working with them required you to tell them precisely what you wanted them to do (for instance, “method A exists on class B, please add an equivalent method to classes C through F”). Otherwise they’d go off and do entirely the…
Right now developer experience is measured in seconds. If your tests take a second to run, that’s good; if they take thirty seconds, that’s bad. Any faster than a second doesn’t really matter, because most of your time is spent either thinking or waiting for an AI agent to spin…
Mathematicians are broadly not anti-AI. They’re more culturally open to using AI as a tool than, say, artists or writers. However, now that more and more genuinely prestigious problems have fallen to AI, that might be changing. Almost five thousand mathematicians (including…
Lots of people are making the case that we should stop building software for human users and start building it for AI agents. This kind of makes sense. For instance, my AI agents now use Datadog way more than I use it myself, purely by virtue of them moving much more quickly and…
A recent resignation tweet from an Anthropic researcher has everyone talking about the AI apocalypse again. Among other things, he said: The people building AI earnestly believe that it could kill us all by the end of the decade. Many people found it hard to believe that AI…
Just over a year ago I wrote Why we should anthropomorphize LLMs. Now it’s a hot topic again, driven by Dwarkesh Patel’s description of OpenAI’s recent swarm breakout as a sequence of AI “civilizations”. In 2025, my argument for anthropomorphism went like this: AIs are trained…
Automated AI text detection is currently an underserved niche. The only game in town is Pangram, which does an excellent job but desperately needs more competition. In a few years, I would be surprised if every major social network doesn’t scan new posts and comments for AI…
A lot of people think that good leadership requires radical responsibility. Conscious Leadership defines it like this: Taking full responsibility for one’s circumstances (physically, emotionally, mentally and spiritually) is the foundation of true personal and relational…
“Workslop” is when your colleagues or bosses communicate with you by pasting big chunks of AI-generated text. The core problem with workslop is that the effort involved is asymmetrical, like a denial-of-service attack: it takes almost no effort to produce text with AI, but it…