seangoedecke.com RSS feed
Description
Feed Activity
Latest Posts
Why we should anthropomorphize LLMs
I recently read a very good blog post by Halvar Flake titled “A non-anthropomorphized view of LLMs”. Here’s a very brief summary: LLMs are just a mapping function between language...
Mecha-Hitler, Grok, and why it's so hard to give LLMs the right personality
Recently, xAI’s Grok model made some very strange comments. In a now-deleted post, it suggested Adolf Hitler as the right person to deal with “anti-white hate”. It also pointed out...
The more senior engineers get, the more results matter
In my experience, people tend to overrate how much moving up the org chart changes the fundamentals of the job. As a staff engineer, I do more or less the...
How I use LLMs to learn new subjects
If you want to learn about a new subject in 2025, one of the best ways to do it is to ask a strong language model. The reason this method...
How to become passionate about delivering shareholder value
I am passionate about delivering shareholder value. It feels kind of embarrassing to admit, but it’s true1. I like all the things an engineer is supposed to like - writing...
Building tiny AI tools for developer productivity
The two current paradigms of AI app development are agentic coding (using an AI to help you write your ordinary line-of-business code faster) and building AI apps for mass consumption...
What happens when engineers work more than one job
There’s a news story going around about an engineer called Soham1 who was routinely “overemployed”: he maintained remote jobs at multiple tech companies simultaneously, collecting their salaries in parallel. When...
Continuous AI in software engineering
When I use AI in my software engineering job, I use it “on tap”: when I have a problem that I’d like to run past the LLM, I go and...
I don't care if my manager writes code
I write a lot about how the post-2010s economic squeeze has made it harder to be a software engineer at a large tech company. But I haven’t said much about...
AI coding agents are already commoditized
All of a sudden, it’s the year of AI coding agents. Claude released Claude Code, OpenAI released their Codex agent, GitHub released its own autonomous coding agent1, and so on...
Pure and impure software engineering
Why do solo game developers tend to get into fights with big tech engineers? Why do high-profile external hires to large companies often fizzle out? Why is AI-assisted development amazing...
Everything I know about good system design
I see a lot of bad system design advice. One classic is the LinkedIn-optimized “bet you never heard of queues” style of post, presumably aimed at people who are new...
What's going to happen to junior engineers?
In the 2010s, companies were hiring a lot of juniors. This was partially an economic decision: companies were hiring everyone, and juniors were a lot cheaper and easier to hire...
Is this your brain on ChatGPT?
A recent MIT study - titled “Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task” - has been making the rounds. I...
Every service should have a killswitch
The more time you spend designing systems, the more paranoid you get about things going wrong. The most experienced and paranoid engineers I know build a killswitch into every single...
Say "but yes", not "yes but"
When you’re agreeing with someone but you have a caveat, don’t say “yes, but”. Instead, say “but yes”. For instance, if you’re happy with a suggested approach so long as...
The first big AI disaster is yet to happen
The first public passenger locomotive, Locomotion No. 1, began service in September 1825. The first mass-casualty railway disaster happened seventeen years later, in May 1842. A train to Paris derailed,...
The illusion of "The Illusion of Thinking"
Very recently (early June 2025), Apple released a paper called The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity. This has...
AI interpretability is further along than I thought
It’s common to call AI language models “black boxes”. Unlike normal human-written programs, which we can examine line-by-line to see what they’re doing, AI models are grown. AI models make...
Arguing point-by-point considered harmful
Engineers love to have technical discussions point-by-point: replying to every idea in turn, treating each as its own mini-discussion. It just makes sense! A good engineer has multiple reasons for...