Ben Congdon

TL;DR: “Private by obscurity” has been dissolved.

The rise of coding agents has made it easy for a single engineer to spend thousands of dollars a day in LLM tokens.

Coding agents and reasoning models let individuals consume many more LLM tokens than they could a year ago.

In late January, I published a post1 (archive) on the Databricks engineering blog about “SAFE”, the feature flagging and experimentation platform I’ve been working on for the past few years.

Previously: 2024 , 2023 , 2022, 2021, 2020, 2019, 2018, 2017 A surprisingly persistent personality quirk I have is that I care a lot about the changeover of the new year.

A few days ago I tumbled down some stairs and managed to bruise both of my knees.

Over the holidays, I’ve been thinking about what the impacts of 2025’s progress in AI coding tools will mean for how software gets designed, built, and operated in 2026.

I’ve been thinking a lot about watches over the past few months – like a lot about watches.

I’m about half a dozen flights into training for a Private Pilot’s License and wanted to write some notes while I’m still firmly in the “beginner mindset”. 𐡸 Flight training has tons and tons of mnemonics.

David Chalmers recently wrote a thought-provoking paper on the nature of conversational LLM entities, titled “What We Talk to When We Talk to Language Models”.

Previous book lists: 2022, 2021, 2020, 2019, 2018.

Today is Christmas Eve, which puts us in that liminal few weeks of the holiday season that serve as useful time for reflection.

I’ve been having a bunch of fun in Rust recently.

I sometimes wish I’d grown up in the era of written letters, or that email and long-form written correspondences were more fashionable than they currently are.

Salvatore Sanfilippo, aka antirez, the creator of Redis, posted a piece on his reflections on AI for the end of 2025.

From Gas Works Park, you can watch jets descend to SeaTac in a steady stream, one every minute or two.

2025 was a really good year for music for me.

Judge a man by his questions rather than by his answers. – Voltaire I am an introvert by nature, but I come alive for a good conversation.

In the end, we self-perceiving, self-inventing, locked-in mirages are little miracles of self-reference. … Our very nature is such as to prevent us from fully understanding its very nature. – Douglas R.

From Dwarkesh Patel: Unreasonably effective writing advice: “What are you trying to say here?

This is post 15 of my unannounced, self-imposed month of daily writing.

The thing that separates life from non-life is information. - Paul Davies I’ve probably learned about the thought experiment of Maxwell’s demon at least half a dozen times – in multiple physics courses, in multiple books.

I’ve been using Chorus for the past 6-7 months.

In late 2022, I had a conversation with a senior engineer on the coming problem of “what to do when AI is writing most of the code”.

I recently encountered a fun performance problem.

I review a lot of PRs these days.

How does a distributed system reliably determine when one of its members has failed?

1.

1.

Source 1.

By default, SQLite tables have a special rowid column that uniquely identifies each row.

Last Sunday, I ran the 2025 Seattle Marathon.

1.

I’ve recently started on the journey to get a private pilot’s license.

I enjoy conversations, particularly with people I care about.

As my team’s summer interns finished up their rotations this week, I had my usual end-of-internship “AMA” 1:1s.

There’s a line in Ben Kuhn’s essay, “Impact, agency, and taste”, that’s been rattling around in my head lately.

On June 12, 2025, most of GCP went offline.

I had the realization a year or so ago that much of the high-impact work I’ve done in my career has been related – directly or indirectly – to building developer tooling.

Since I wrote about COCONUT, Meta’s paper on reasoning in latent space, there’s been a wave in publicly accessible research into reasoning models.

Previously: Mid 2024 The landscape of AI tooling continues to shift, even in the past half year.

The impetus for this post was my recent realization that I’ve developed an involuntary reflex for spotting AI-generated content.

Recent advances in LLMs have demonstrated increasingly powerful reasoning capabilities, primarily through eliciting chain-of-thought outputs from models.

I lived in the Eastlake neighborhood of Seattle for several years.

I haven’t been writing much recently (sound of crickets coming from this year’s blog archive), but this is such an OnBrand™ post that I couldn’t not write it.

I’ve been in a mode of trying lots of new AI tools for the past year or two, and feel like it’s useful to take an occasional snapshot of the “state of things I use”, as I expect this to continue to change pretty rapidly.

I’ve recently been contemplating a recurring pattern that I’ve observed in several teams I’ve worked on – the ‘Load-Bearing Script.’

I recently read Pema Chödrön’s Living Beautifully, and I was struck by the following passage: Chögyam Trungpa demonstrated the co-emergent nature of feelings in a teaching on boredom-on how we feel when nothing’s happening.

Two of my all-time favorite articles about managing one’s energy and time relate to the notion of maintaining “Slack” in one’s life.

I recently got an M2 MacBook Air to replace my 2014 MacBook Pro.