Paul Badcock

[tobi lutke @tobi]

I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc.

Insisting on only reading CLAUDE.md sometimes leads to split brain problems when different team members use different tools. Just unnecessary.

[Paul Badcock @p_badcock]

Can you do an info video or posting some time oh how your pylons work @SailGP! Are they autonomous gps based boats or is someone out there with a fishing trolling motor and Google Maps?

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Paul Badcock @p_badcock]

Come to terminal 3 in #pearson airport in #Toronto where you too can worry about exposure to avian flu.

[Paul Badcock @p_badcock]

@statusisdown Seems like most of these downtimes are in Akamai edge?

[Paul Badcock @p_badcock]

Huzza MacOS 15.3 fixed hardware token not working in Safari that broke in 15.2 #MACOS

[the tiny corp @__tinygrad__]

@luka_emon When I started, I didn't understand where the problems lie with AMD. I thought it was the driver, it's not. tinygrad is now submitting AQL queues directly to the GPU.

It's the firmware, and it might even be the hardware.

NVDA deserves to be king.

[Paul Badcock @p_badcock]

@XenosNS Maybe this is post new ui on the dashboard so don’t know if it’s a new symptom but the system was flawless till then. Kinda scary as the fumes were overpowering that I thought something had caught fire

[Paul Badcock @p_badcock]

Xbox Series X burnt up yesterday. It had no prior problems but was sitting at the Minecraft game menu when a strong electronic burning smell was present. Seems like such a random event for it to overheat and break #XboxSeriesX #Microsoft #Xbox

[Dave Callan | dotnet @Dave_DotNet]

#dotnet Performance Improvements 🚀

.NET 8
https://t.co/aYltk7Gdl6

.NET 7
https://t.co/RKl5bB5XwZ

.NET 6
https://t.co/tLAHAm7lE3

.NET 5
https://t.co/5NZONp6VpZ

.NET 3.0
https://t.co/LW33NSRC48

.NET 2.1
https://t.co/r57tQPIVdq

.NET 2.0
https://t.co/MsCPhLbWGs

Bookmark it!

[DevOps on Azure @AzureDevOps]

We found an interesting article on running containers in #Azure @ThePracticalDev.

It has some good analysis, tons of helpful advice, and some helpfully, explanatory flow charts 😉. Give it a look-over. 📖 https://t.co/dXt0pCOhmq

[Dave Callan | dotnet @Dave_DotNet]

What version of .NET are you using for the majority of your prod apps?

I took the poll below ⬇ recently. A lot of devs still on .NET Framework. Many stick with .NET 6 rather than 7 as it's LTS.

How did your last upgrade go?

#dotnet #csharp

[Paul Badcock @p_badcock]

@geerlingguy aaaand its gone!

[Paul Badcock @p_badcock]

@HRMFireNews municipal groups chopper putting work in on farmers dairy lane area #NSFire

[Paul Badcock @p_badcock]

@FungiwithBengi Agreed hopefully it shows the need for satellite bases at major airports i key areas of the province. Perhaps a fleet or contracted fleet shared with the rest of the maritimes as Newfoundland is sharing three.

[Paul Badcock @p_badcock]

Looks to be constant flights of https://t.co/lkB2UcGEYC from NB to Shelburne fire #nsfire

[Paul Badcock @p_badcock]

@FungiwithBengi Looks like it or it’s quicker to use their own facilities the. Try to establish something here in Nova Scotia. And another wave coming in https://t.co/sFz2DOqW6A

[Paul Badcock @p_badcock]

@HRMFireNews https://t.co/zMcu6lB0bE

It’s been working since yesterday I think.

[Paul Badcock @p_badcock]

Anyone hear if there’s a fire or hot spot in hants county? #nsfire

[Paul Badcock @p_badcock]

More coming in as it looks like the first four are returning to base #nsfires