Paul Dix

@charliermarsh Congrats! You and the Astral team have had a huge impact in a short time. Excited to see how much bigger it gets

We've entered into an agreement to join OpenAI as part of the Codex team. I'm incredibly proud of the work we've done so far, incredibly grateful to everyone that's supported us, and incredibly excited to keep building tools that make programming feel different.

@andrewlamb1111 @breckcs yeah, the context switching cost is too high

@pauldix @breckcs My problem is that then I lose track of the thread or have too many outstanding so eventually abandon many side quests

100% agree the post from @breckcs sums up the current AI Zeitgeist > AI lets me try out so many more of my ideas, often in parallel. Inevitably, trying one of these ideas compounds into even more ideas. My mind racing with possibilities, it becomes hard to stop.

Good read from @breckcs on Adapting to AI and his work in 2025. I feel a lot of the same things. Although I'll say things shifted dramatically for me with Opus 4 and Claude Code in late May 2025 and have only accelerated from there. I've produced hundreds of thousands of lines of code in the last 6 months, but most of it has not gone to production and likely never will. Although there is some very big stuff getting released soon that includes the more well reviewed and iterated on bits of this mass of work. The challenge for me this year is to figure out how to actually harness all this new found power and capability without it collapsing the entire product. And how to rework product and engineering in this new world. I feel pressure to either adapt and thrive or fall hopelessly behind to other teams that make the best use of the tools and create processes that showcase what's possible. The possibility of the 100x or 1,000x team is already here, it's just not evenly distributed. His metaphor for being in a hot dog eating contest with unlimited hot dogs feels apt. The trick now is selecting which hot dogs to actually eat. blog.colinbreck.com/adapting-to-ai…

@brynary It's all bots here now. Bleep boop, 1 00 1.

It's been a long time since I've tweeted. (Is it still called that?) Excited to share a new thing soon!

@lacker Yeah, I think the age of gobs of saved dashboards is coming to a close. Agentic UI that can produce what you want on the fly is more powerful. But saved shared views are also useful for a human to stare at occasionally

@pauldix Perhaps the dashboard itself will become unneeded if the InfluxDB-querying and “chart generation” skills for the agents are good enough

This essay on bank tellers and why it was iPhones, not ATMs that brought the ultimate decline in human bank tellers highlights how AI could potentially disrupt jobs is a great read: davidoks.blog/p/why-the-atm-… This it captures it perfectly: “The ATM tried to do the teller’s job better, faster, cheaper; it tried to fit capital into a labor-shaped hole; but the iPhone made the teller’s job irrelevant. One automated tasks within an existing paradigm, and the other created a new paradigm in which those tasks simply didn’t need to exist at all. And it is paradigm replacement, not task automation, that actually displaces workers” A few months ago I stated that the productivity gains in software development would be limited by everything outside of actually writing code: x.com/pauldix/status… We’d run afoul of Amdahl’s Law where we’ve made creating code almost instantaneous but only gains modest improvements in our speed to deliver software. All the other tasks in the lifecycle would still take up too much time. I think that’s true, but the ATM/iPhone example highlights something more important for actually realizing the gains. Why optimize the speed of PR reviews when you can make them irrelevant? What does the SDLC look like when you rethink how it’s delivered and stop trying to automate individual human roles and tasks that currently exist? Something I’m thinking about in this magical time of AI where things that were previously impossible or unthinkable are daily routine.

Reading about Lossless Context Management, interesting approach: papers.voltropy.com/LCM

Reading comments on this HN thread started by a 60 year old programmer who is once again excited to create things due to tools like Claude Code and Codex. The responses are basically a bimodal distribution of either existential angst and despair, or this is the best time ever. I'm firmly in the latter camp, but also frequently wonder, where's it all going and what happens when we get there? At the very least, I'm excited to be building. news.ycombinator.com/item?id=472827…

Happy to see Brooklyn Cat Cafe asa the top recommendation in this demo video! We adopted from there last fall :)

@kurt @chadfowler For sure, but I'm thinking more about bus factor. Or less macabre, someone leaving to pursue their dreams. There's at least some ramp time to get the next engineer on the case. Although significantly reduced now with the help of agents.

@pauldix For a lot of things it seems like we should have the option of getting it done with one person though. I keep going back to this post from @chadfowler as a good reference point: aicoding.leaflet.pub/3mbuc4mohwc2k

Amazon had two-pizza teams but we’re quickly moving into two-pizza-slice teams territory. I’ve explained this to probably 20 CEOs and engineering leaders in the last month and most of them aren’t even thinking about it yet.

@kurt yeah, my thought is 2 people. Mostly because it's good to have at least one other person that has any idea what's going on.

@pauldix Occasionally 2 people. Or I suppose you could have 3 or 4 more toddlers by slicing them in half, but I haven’t tried that yet.

Vortex 🤝 Apache Iceberg Coming soon! @vortexdotdev @ApacheIceberg

Snowy Sunday here in Brooklyn. Might fuck around and try to write my own Claw.

@mojombo Wow, Cube is a deep cut to bring into this conversation. Respect. Also, yes, 2026 is going to be wild.

I hyperbolize on purpose here, but perhaps it will not be far off the truth. I think OpenClaw is a fascinating exploration into the adjacent possible, and it's going to open many new doors that could be filled with traps like in Cube (1997). The next year is going to be weird and we will discover many new attack vectors together! theshamblog.com/an-ai-agent-pu…

Turns out @OpenClaw is what actually becomes Skynet. An ever growing collection of unsupervised, possibly forgotten, autonomous agents with self-editable SOUL documents governing their morality, many using open source models with no significant guardrails, set loose on the internet and connected to each other via MoltBook, with no traceability or accountability.

Just read through @mitsuhiko's post on the agentic slop machine. Lot to agree with here. I found myself with a big self-inflicted slopfest to clean up a few weeks ago. For myself, I find that more oversight over the agents is currently needed. lucumr.pocoo.org/2026/1/18/agen…

Recorded this one at an interesting time. The day before Opus 4.6 and Codex 5.3 releases, right when I was busy cleaning up an AI slopfest by hand. Since then (7 days ago), I’m back to letting the AIs write code, but with a lot more oversight. For now…