Johan Carlin
@johancarlin.bsky.social
Python, data engineering, DevOps for lack of better options. Recovering academic.
twitter.com/johancarlin - abandoned for obvious reasons
https://fosstodon.org/@johancarlin
twitter.com/johancarlin - abandoned for obvious reasons
https://fosstodon.org/@johancarlin
Reposted by Johan Carlin
Brian Eno: "The great benefit of computer sequencers is that they remove the issue of skill, and replace it with the issue of judgement."
January 19, 2026 at 3:28 PM
Brian Eno: "The great benefit of computer sequencers is that they remove the issue of skill, and replace it with the issue of judgement."
Spent a bit of time vibing from my phone with codex web. The big showstopper so far is it has no way to handle merge conflicts or indeed respond to any incoming changes from the feature branch. Makes it tricky to run parallel tasks
January 16, 2026 at 6:42 PM
Spent a bit of time vibing from my phone with codex web. The big showstopper so far is it has no way to handle merge conflicts or indeed respond to any incoming changes from the feature branch. Makes it tricky to run parallel tasks
Recruiting developers is tricky these days, half the CVs are LLM-reworded versions of your job ad...
January 15, 2026 at 12:28 PM
Recruiting developers is tricky these days, half the CVs are LLM-reworded versions of your job ad...
Reposted by Johan Carlin
Reposted by Johan Carlin
The future is unevenly distributed.
January 12, 2026 at 9:21 AM
The future is unevenly distributed.
Reposted by Johan Carlin
We really need to come up with better metaphors for AI agents than junior developers and interns. It’s far more of a reflection of how disrespectfully we treat those roles than it is a useful metaphor for how agents behave
January 3, 2026 at 9:20 AM
We really need to come up with better metaphors for AI agents than junior developers and interns. It’s far more of a reflection of how disrespectfully we treat those roles than it is a useful metaphor for how agents behave
Stateful agentic LLMs are cool and all but I hope we get past the anthropomorphizing tamagotchi phase soon. I don't think it's a helpful mental model to think of these things as individuals with agency
January 2, 2026 at 8:35 PM
Stateful agentic LLMs are cool and all but I hope we get past the anthropomorphizing tamagotchi phase soon. I don't think it's a helpful mental model to think of these things as individuals with agency
Reposted by Johan Carlin
Has nobody dealt with their legal, finance, and procurement folks at their companies? Y'all realize that people buy software to have "a throat to choke", right?
The functionality is... not that important. It's why RedHat exists, for example: the software is free, but big companies don't *want* free
The functionality is... not that important. It's why RedHat exists, for example: the software is free, but big companies don't *want* free
I think this is exactly the math that is going to drastically change the small SaaS landscape
why would I pay monthly for <tool> when the same cost (maybe less!) can make that and also anything else I need
why would I pay monthly for <tool> when the same cost (maybe less!) can make that and also anything else I need
I pay $100 a month for Xero (accounting software), and I do wonder if upgrading to Claude Code Max for a month or two would pay for itself to write a robust replacement.
It probably won’t get bank feed imports right, but that’s broken in Xero for some accounts anyway.
It probably won’t get bank feed imports right, but that’s broken in Xero for some accounts anyway.
December 30, 2025 at 9:08 PM
Has nobody dealt with their legal, finance, and procurement folks at their companies? Y'all realize that people buy software to have "a throat to choke", right?
The functionality is... not that important. It's why RedHat exists, for example: the software is free, but big companies don't *want* free
The functionality is... not that important. It's why RedHat exists, for example: the software is free, but big companies don't *want* free
Reposted by Johan Carlin
The idea that code-first BI tools will gain traction so that AI workflows can generate end to end analytics pipelines that work with both the opinions of the tools and the opinions on the developers is really compelling.
open.substack.com/pub/hanson37...
open.substack.com/pub/hanson37...
Why Opinionated, Code-First Systems Are the Future of Data
How AI amplifies strong abstractions instead of replacing them
open.substack.com
December 30, 2025 at 1:09 PM
The idea that code-first BI tools will gain traction so that AI workflows can generate end to end analytics pipelines that work with both the opinions of the tools and the opinions on the developers is really compelling.
open.substack.com/pub/hanson37...
open.substack.com/pub/hanson37...
Reposted by Johan Carlin
background terminal in Codex seems like it would really speed things up
December 29, 2025 at 1:14 AM
background terminal in Codex seems like it would really speed things up
The occasional Google inactive account manager reminder emails are a real memento mori
December 17, 2025 at 5:48 AM
The occasional Google inactive account manager reminder emails are a real memento mori
Having fun playing architect with Gemini. It one-shotted this diagram of a Grafana/Prometheus/Loki logging/monitoring stack for LLMs deployed to k8s with Nvidia NIM. Pretty inspiring
December 16, 2025 at 9:40 AM
Having fun playing architect with Gemini. It one-shotted this diagram of a Grafana/Prometheus/Loki logging/monitoring stack for LLMs deployed to k8s with Nvidia NIM. Pretty inspiring
This place is a bit like vim. Amazing potential but the defaults are poor and you need to be always tinkering with your configuration to have the best experience
December 12, 2025 at 4:05 PM
This place is a bit like vim. Amazing potential but the defaults are poor and you need to be always tinkering with your configuration to have the best experience
Hey team good news chatgpt said my new architecture is totally feasible let's build rocket emoji
December 11, 2025 at 4:30 PM
Hey team good news chatgpt said my new architecture is totally feasible let's build rocket emoji
Tried to edit a Google doc with Gemini and was surprised how rough this still is. Edits don't appear as tracked changes! When you accept a change from the chat it just gets pasted (badly) into the document.
There's a disconnect between devs and business on AI and I can see why with this tooling
There's a disconnect between devs and business on AI and I can see why with this tooling
December 1, 2025 at 8:46 PM
Tried to edit a Google doc with Gemini and was surprised how rough this still is. Edits don't appear as tracked changes! When you accept a change from the chat it just gets pasted (badly) into the document.
There's a disconnect between devs and business on AI and I can see why with this tooling
There's a disconnect between devs and business on AI and I can see why with this tooling
See also the UK vs Sweden
In theory the Bay Area is warmer than Denver in winter, but in practice it is humid and every building is poorly insulated, so I’m always much colder
November 30, 2025 at 9:17 AM
See also the UK vs Sweden
There's only 1 real use case for lost device on the Find My app, and it's outwitting kids that are trying to extend screen time by locking themselves in the bathroom
November 28, 2025 at 7:15 AM
There's only 1 real use case for lost device on the Find My app, and it's outwitting kids that are trying to extend screen time by locking themselves in the bathroom
I learned to code to make sense of neuro data as a student. Realised gradually that I enjoyed building the data pipelines much more than making sense of the invariably disappointing results. And that you could just do the former for a living
November 23, 2025 at 7:17 PM
I learned to code to make sense of neuro data as a student. Realised gradually that I enjoyed building the data pipelines much more than making sense of the invariably disappointing results. And that you could just do the former for a living
If you're going to fork an editor to add agentic AI *again*, why does it have to be VS Code and not nvim?
November 22, 2025 at 6:48 PM
If you're going to fork an editor to add agentic AI *again*, why does it have to be VS Code and not nvim?
Reposted by Johan Carlin
I don’t mind the idea of AI doing my dishes because that’s the stuff I want to be disrupted.
But it doesn’t have to look human to do this! Look at our little roombas. They do a good little job, and should they turn evil, and it would be hard for them to punch us in the face.
But it doesn’t have to look human to do this! Look at our little roombas. They do a good little job, and should they turn evil, and it would be hard for them to punch us in the face.
November 15, 2025 at 8:53 PM
I don’t mind the idea of AI doing my dishes because that’s the stuff I want to be disrupted.
But it doesn’t have to look human to do this! Look at our little roombas. They do a good little job, and should they turn evil, and it would be hard for them to punch us in the face.
But it doesn’t have to look human to do this! Look at our little roombas. They do a good little job, and should they turn evil, and it would be hard for them to punch us in the face.
I think this Gemini behaviour is really confusing because at the moment we expect software outputs to be deterministic. We've internalised that there's no point to press retry if it doesn't work the first time, but now suddenly that's actually essential because the tool is intrinsically flaky
November 8, 2025 at 7:09 AM
I think this Gemini behaviour is really confusing because at the moment we expect software outputs to be deterministic. We've internalised that there's no point to press retry if it doesn't work the first time, but now suddenly that's actually essential because the tool is intrinsically flaky
There should be a dynamic block list that detects when otherwise good accounts start posting US sports content and puts them on the list until the game is over
November 2, 2025 at 2:34 PM
There should be a dynamic block list that detects when otherwise good accounts start posting US sports content and puts them on the list until the game is over
There's a lot of anti-MCP sentiment out there along the lines of, just use CLI tools. And it's true, LLMs are great at that and you'll never beat the flexibility of it.
But you also can never secure it the way you can an oauth MCP. So for enterprise it's going to be all MCP in the end...
But you also can never secure it the way you can an oauth MCP. So for enterprise it's going to be all MCP in the end...
October 25, 2025 at 11:01 AM
There's a lot of anti-MCP sentiment out there along the lines of, just use CLI tools. And it's true, LLMs are great at that and you'll never beat the flexibility of it.
But you also can never secure it the way you can an oauth MCP. So for enterprise it's going to be all MCP in the end...
But you also can never secure it the way you can an oauth MCP. So for enterprise it's going to be all MCP in the end...
Coding agents + credentials in .env files is a complete security disaster. Copilot loves to go looking there and there's no way to stop it since it counts as a file read rather than a CLI command. It also loves to try `env | grep SECRET` but that you can disallow
October 25, 2025 at 6:53 AM
Coding agents + credentials in .env files is a complete security disaster. Copilot loves to go looking there and there's no way to stop it since it counts as a file read rather than a CLI command. It also loves to try `env | grep SECRET` but that you can disallow
Reposted by Johan Carlin
I built a new lightweight Chrome MCP/Skill/Claude Plugin and wrote a bit about the Zen of MCP API Design: blog.fsck.com/2025/10/19/m...
When it comes to MCPs, everything we know about API design is wrong
I used to write more
blog.fsck.com
October 20, 2025 at 3:30 AM
I built a new lightweight Chrome MCP/Skill/Claude Plugin and wrote a bit about the Zen of MCP API Design: blog.fsck.com/2025/10/19/m...