Welcome to dkdc.dev! This is the Nth iteration of my website.

I use Microsoft Edge and need >134GBs of RAM for my terminal (yeah I vibe code)

OpenAI's codex has demonstrated something I've struggled to for a while: we've been doing AI software engineering wrong. Or at least, there's a better way with CLIs and files as the interface. What's old is new again.

Welcome to dkdc.dev! This is the Nth iteration of my website.

I suspect banning advertisement -- at least digital advertisement -- would make the world a better place.

"FUCK!"

Last week there was a disaster and that disaster has a name.

I would like to abolish the term RAG and instead just agree that we should always try to provide models with the appropriate context to provide high quality answers.

- Hamel Husain

This is important. Obfuscating how to use the language boxes with dumb jargon isn't helpful.

- Cody

Looking at LLMs as chatbots is the same as looking at early computers as calculators. We’re seeing an emergence of a whole new computing paradigm, and it is very early.

— Andrej Karpathy

• Simon Willison

- Cody

https://amasad.me/meta

I've first noticed this problem in the startup world where you see famous people that sell books, talk at conferences, and tweet advice to founders, but when you take a closer look, they've never done much founding themselves. They're like the "entrepreneurship" professor that never built a business. They're experts in the metagame -- they're polished speakers, engaging writers, and thought-leadering tweeters. The problem, though, is that they're not judged by customers, the market, or nature, instead they're judged by their peers. I call them metapreneurs.

This is an instance of what Nassim Taleb calls "The Expert Problem" -- when other experts and meta-experts judge experts. Eventually the lack of contact with reality will corrupt the field. In the sciences, that lead to the replication crisis and the absurdities of the humanities.

If you find yourself going to a lot of conferences, opining too much on the latest fad in your field, and talking more about doing the thing than doing the job itself, then you, my friend, are getting sucked into the metagame.

• Amjad Masad

The bane of my existence:

InvalidRequestError: This model's maximum context length is 32768 tokens. However, you requested 33013 tokens (31413 in the messages, 1600 in the completion). Please reduce the length of the messages or completion.

Somebody please give me GPT5-64k access.

See part 1.