Sean Goedecke
Subscribe
Archives
Trying to impress engineers, trying to impress managers
August 1, 2025
Read it on seangoedecke.com In the first few years of my career, I knew next to nothing about how to do good work in a tech company. The senior and staff...
The refusal problem in AI language models
July 29, 2025
Read it on seangoedecke.com Everyone’s interested in what language models can do. But what about what they will do? Try giving ChatGPT 4o a menial task that...
Can small AI models think as well as large ones?
July 26, 2025
Read it on seangoedecke.com An AI trend that’s emerged in the last few months1 is the idea of a “cognitive core”. Instead of trying to build the largest,...
What kind of work I want (in 2025)
July 24, 2025
Read it on seangoedecke.com In 2021, I wrote this post describing the kind of work I wanted then. Almost five years later, it’s time for an update. What kind...
Do not yell at the language model
July 24, 2025
Read it on seangoedecke.com A few days ago, the news went viral that Replit’s AI coding agent went rogue and deleted a production database. A lot has been...
The silent AI war inside tech companies
July 19, 2025
Read it on seangoedecke.com I recently wrote an article for LeadDev about how software engineers are dealing with the AI hype in practice. Here’s my...
The case for regulating AI companions
July 18, 2025
Read it on seangoedecke.com In April, OpenAI screwed up by releasing a version of GPT-4o that was overly sycophantic. If you told it that Brian Cox was...
How to actually use Model Context Protocol
July 17, 2025
Read it on seangoedecke.com Everyone’s very excited about Model Context Protocol, or MCP for short. In a sentence, MCP is a universal protocol for exposing...
Practical notes on getting LLMs to generate new ideas
July 15, 2025
Read it on seangoedecke.com Large language models struggle to generate new ideas. To AI skeptics, this seems trivially true, since they believe LLMs can only...
Building a RTS where you issue orders to AI agents
July 14, 2025
Read it on seangoedecke.com I’ve always been interested by the third-act turn in Ender’s Game where the child strategists switch from directly controlling...
The three great virtues of an AI-assisted programmer
July 13, 2025
Read it on seangoedecke.com In 1991, Larry Wall famously wrote that the three great virtues of a programmer were “laziness, impatience, and hubris”. A...
METR's AI productivity study is really good
July 10, 2025
Read it on seangoedecke.com I complain a lot on this blog about AI studies. Given that, I ought to give credit when an AI study comes out that I think is...
Why we should anthropomorphize LLMs
July 9, 2025
Read it on seangoedecke.com I recently read a very good blog post by Halvar Flake titled “A non-anthropomorphized view of LLMs”. Here’s a very brief summary:...
Mecha-Hitler, Grok, and why it's so hard to give LLMs the right personality
July 9, 2025
Read it on seangoedecke.com Recently, xAI’s Grok model made some very strange comments. In a now-deleted post, it suggested Adolf Hitler as the right person...
The more senior engineers get, the more results matter
July 8, 2025
Read it on seangoedecke.com In my experience, people tend to overrate how much moving up the org chart changes the fundamentals of the job. As a staff...
How I use LLMs to learn new subjects
July 8, 2025
Read it on seangoedecke.com 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...
Building tiny AI tools for developer productivity
July 5, 2025
Read it on seangoedecke.com The two current paradigms of AI app development are agentic coding (using an AI to help you write your ordinary line-of-business...
How to become passionate about delivering shareholder value
July 4, 2025
Read it on seangoedecke.com I am passionate about delivering shareholder value. It feels kind of embarrassing to admit, but it’s true1. I like all the things...
What happens when engineers work more than one job
July 2, 2025
Read it on seangoedecke.com There’s a news story going around about an engineer called Soham1 who was routinely “overemployed”: he maintained remote jobs at...
Continuous AI in software engineering
July 1, 2025
Read it on seangoedecke.com 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...
I don't care if my manager writes code
June 26, 2025
Read it on seangoedecke.com 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...
AI coding agents are already commoditized
June 25, 2025
Read it on seangoedecke.com All of a sudden, it’s the year of AI coding agents. Claude released Claude Code, OpenAI released their Codex agent, GitHub...
Pure and impure software engineering
June 21, 2025
Why do solo game developers tend to get into fights with big tech engineers? Read it on seangoedecke.com Why do solo game developers tend to get into fights...
Everything I know about good system design
June 20, 2025
Read it on seangoedecke.com I see a lot of bad system design advice. One classic is the LinkedIn-optimized “bet you never heard of queues” style of post,...
What's going to happen to junior engineers?
June 20, 2025
I'm worried about the impact of AI on the market for juniors. Read it on seangoedecke.com In the 2010s, companies were hiring a lot of juniors. This was...
Is this your brain on ChatGPT?
June 19, 2025
Is this your brain on ChatGPT? Read it on seangoedecke.com A recent MIT study - titled “Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an...
Every service should have a killswitch
June 19, 2025
Every service should have a killswitch Read it on seangoedecke.com The more time you spend designing systems, the more paranoid you get about things going...
Say "but yes", not "yes but"
June 13, 2025
Say "but yes", not "yes but" Read it on seangoedecke.com When you’re agreeing with someone but you have a caveat, don’t say “yes, but”. Instead, say “but...
The first big AI disaster is yet to happen
June 10, 2025
The first big AI disaster is yet to happen Read it on seangoedecke.com The first public passenger locomotive, Locomotion No. 1, began service in September...
The illusion of "The Illusion of Thinking"
June 7, 2025
The illusion of "The Illusion of Thinking" Read it on seangoedecke.com Very recently (early June 2025), Apple released a paper called The Illusion of...
AI interpretability is further along than I thought
June 7, 2025
AI interpretability is further along than I thought Read it on seangoedecke.com It’s common to call AI language models “black boxes”. Unlike normal human-...
Arguing point-by-point considered harmful
June 6, 2025
Arguing point-by-point considered harmful Read it on seangoedecke.com Engineers love to have technical discussions point-by-point: replying to every idea in...
John Henry and the large language model
June 3, 2025
John Henry and the large language model Read it on seangoedecke.com John Henry told his captain A man ain’t nothing but a man But before I let your steam...
Why DeepSeek is cheap at scale but expensive to run locally
May 31, 2025
Why DeepSeek is cheap at scale but expensive to run locally Read it on seangoedecke.com Why is DeepSeek-V3 supposedly fast and cheap to serve at scale, but...
It's not your codebase
May 30, 2025
It's not your codebase Read it on seangoedecke.com Engineers often feel a lot of ownership over the code they write. That’s understandable: it’s partially...
How does ChatGPT work? What is AI, really?
May 26, 2025
How does ChatGPT work? What is AI, really? Read it on seangoedecke.com How does AI work? Since 2022, it’s been possible to have a conversation with a...
How projects fail at large tech companies
May 25, 2025
How projects fail at large tech companies Read the original post at seangoedecke.com How do projects fail at large tech companies? As I've said many times,...
In defense of shallow technical knowledge
May 24, 2025
In defense of shallow technical knowledge Read it on seangoedecke.com Whenever a new piece of technology comes out (these days, mostly AI) I go to some...
Practical AI techniques for daily engineering work
May 23, 2025
Practical AI techniques for daily engineering work Read it on seangoedecke.com Popular advice about using AI is obsessed with tools and “magic prompts”. To...
Strengths and limitations of diffusion language models
May 22, 2025
Strengths and limitations of diffusion language models Read it on seangoedecke.com Google recently released Gemini Diffusion, which is impressing everyone...
Practical advice for engineers in these troubled times
May 20, 2025
Practical advice for engineers in these troubled times Read it on seangoedecke.com Since 2023, the rise of interest rates has caused a sea change in how...
Diffusion models explained simply
May 19, 2025
Diffusion models explained simply Read it on seangoedecke.com Transformer-based large language models are relatively easy to understand. You break language...
Why strong engineers are rarely blocked
May 18, 2025
Why strong engineers are rarely blocked Read it on seangoedecke.com Earlier in my career I used to get blocked1 constantly, but these days it’s rare. What...
Patience is the killer LLM feature
May 16, 2025
Patience is the killer LLM feature Read it on seangoedecke.com Sam Altman, CEO of OpenAI, famously said that his goal was to make intelligence “too cheap to...
New posts from Sean Goedecke
May 12, 2025
Thank you for subscribing! Bear with me as I figure out how to send these emails. Here are the blog posts I wrote this week: Why can't language models come...
Blog
GitHub
LinkedIn