RSS.Social

seangoedecke.com RSS feed

follow: @[email protected]

Posts

Big tech engineers need big egos

I don't know if my job will still exist in ten years

Giving LLMs a personality is just good engineering

Insider amnesia

What's so hard about continuous learning?

LLM-generated skills work, if you generate them afterwards

Two different tricks for fast LLM inference

On screwing up

Large tech companies don't need heroes

Getting the main thing right

How does AI impact skill formation?

You have to know how to drive the car

How I estimate work as a staff software engineer

I'm addicted to being useful

Crypto grifters are recruiting open-source AI developers

The Dictator's Handbook and the politics of technical competence

2025 was an excellent year for this blog

Grok is enabling mass sexual harassment on Twitter

Software engineers should be a little bit cynical

You can't design software you don't work on

Nobody knows how large software products work

AI detection tools cannot prove that text is AI-generated

How good engineers write bad code at big companies

Becoming unblockable

Why it takes months to tell if new AI models are good

Only three kinds of AI products actually work

Writing for AIs is a good way to reach more humans

To get better at technical writing, lower your expectations

Is it worrying that 95% of AI enterprise projects fail?

Is it worrying that 95% of AI enterprise projects fail?

Why do AI models use so many em-dashes?

Mistakes I see engineers making in their code reviews

Should LLMs just treat text content as an image?

What have we learned about building agentic AI tools?

We are in the "gentleman scientist" era of AI research

How I provide technical clarity to non-technical leaders

GPT-5-Codex is a better AI researcher than me

How I influence tech company politics as a staff software engineer

What is "good taste" in software engineering?

AI coding agents rely too much on fallbacks

Endless AI-generated Wikipedia

What I learned building an AI-driven spaced repetition app

AI is good news for Australian and European software engineers

If you are good at code review, you will be good at using AI agents

The whole point of OpenAI's Responses API is to help them hide reasoning traces

'Make invalid states unrepresentable' considered harmful

An unofficial FAQ for Stripe's new "Tempo" blockchain

Seeing like a software company

Do the simplest thing that could possibly work

Finding the low-hanging fruit

Everything I know about good API design

Don't feed me AI slop

The famous "bottomless pit" AI greentext is fake

Is chain-of-thought AI reasoning a mirage?

What's the strongest AI model you can train on a laptop in five minutes?

OpenAI's new open-source model is basically Phi-5

AI interpretability has the same problems as philosophy of mind

Why I don't allow AI-generated content on my blog

Trying to impress people you don't respect

The refusal problem in large language models

Can small AI models think as well as large ones?

What kind of work I want (in 2025)

Do not yell at the language model

The case for regulating AI companions

How to actually use Model Context Protocol

Vibe coding and the silent AI war inside tech companies

Practical notes on getting LLMs to generate new ideas