Derik Hammer

Narrower scope produces more focused output. When you define what an AI cannot do, what it does accomplish improves. Part 7 of First Principles of AI Usage. sqlhammer.com/index.php/2026…

77% of AI-using engineering teams see minimal productivity gains. Carnegie Mellon's Self-Refine research shows iteration alone improves output by 20%, same model, zero upgrades. The model is not the constraint. The process is. Iterate, Don't Orate: sqlhammer.com/index.php/2026…

I asked AI to build a procedural terrain system in one shot. It ran. Unmaintainable. I decomposed the same task into research, proof-of-concepts, and review gates. The delta in quality was substantial. Monolithic delegation commonly wastes AI capability sqlhammer.com/index.php/2026…

The Amazon Kiro agent deleted a production environment. Not a malfunction; it had permission. The question is never how much to trust AI. The question is whether you've correctly priced the door. New post on calibrating autonomy to stakes: sqlhammer.com/index.php/2026…

The successful businesses will be the ones that use AI to enhance, not downsize. tiktok.com/t/ZTkN8oUMB/

AI cannot own its output. You can. Part 3 of First Principles of AI Usage - Why accountability doesn't shrink when you hand work to an agent; it scales with what the agent can reach. sqlhammer.com/index.php/2026…

I love how AI is never offended. My favorite reply to any of the AI models when some error is encountered. "That sounds like a you problem."

AI does not know what is true. It knows what is statistically probable. Fluent, confident wrong answers are more dangerous than obvious hallucinations. They reach stakeholders before anyone questions them. Your judgment is not optional. sqlhammer.com/index.php/2026…

You are not just writing prompts. You are constructing the informational environment the AI reasons within. The ceiling on output quality is set before you type a single word. Context is the product. Part 1 of my First Principles series: sqlhammer.com/index.php/2026…

@way0utwest Let me know how it goes!

@SQLHammer On my list to try codex. I've been a CC person as well, and it's worked well. I need to give codex a try for something and compare.

I use Claude Code for my more advanced works with AI. However, a friend recently has been talking a lot about Codex. What's your take on when to use either?

That was a great Coronet Heist (DnD 5e) one-shot the other night. I am going to find more time to get back into a TTRPG routine.

"It must take you longer to make it than it takes for the user to consume it. Anything less is the essence of slop." - Unknown

AI as a thought partner is next level! Given the right prompt, AI helps me broaden my thinking and stress tests my assumptions.

When Claude is down

@prattprattpratt Keep up the positive messages. We need more love in this world for all people. Especially those that may disagree with us.

Praying for Charlie Kirk right now, for his wife and young children, for our country. We need God’s grace. God help us.

@jasonhorner Higher skilled candidates could qualify for a higher pay bracket.

@jasonhorner I should have mentioned, 100% remote anywhere in the USA

Are you a DBA who jumped to the development side of the fence? Are you a back-end software engineer who decided to pivot their career into data modeling and data dev work? If so, check this out. DM me when you apply and I will get eyes on your CV. jobs.lever.co/olo/c3236190-8… #sqljobs

How to say, "I estimated," in data speak... "We used a proxy metric to derive this statistic."