Jon

@Azure's having trouble this morning. ADX and App Insights non-responsive.

@G_S_Bhogal 🎯 Writing, like other arts, exists for the purpose of human expression. Code, though there is certainly an art to it, is not art. It is a means to an end.

Coding is telic; it’s done to produce something else. Writing is autotelic; it’s done to produce writing.

2024 PM: How long to implement this user story? Dev: About a week. PM: Really? That long? 2026 Dev: Claude, implement this user story. Claude: Thinking... <switch tasks for 60 seconds> Claude: Ruminating... Dev: Wow. You're *STILL* not done?!

@sesigl @mattpocockuk It doesn't have to be this way. Have the AI agent leave an artifact in the solution that you can point it to as a starting point for future sessions. At the end of meaningful work session, instruct it to update the doc with what it did and "learned."

The lead dev analogy is a useful starting point, but there's a gap that makes it misleading. When you mentor a human teammate, they build context over time. You explain the architecture once, they internalize it, and next sprint they make better decisions independently. The feedback loop compounds. With AI, context resets every session. You're not building a teammate, you're onboarding a new contractor every morning. The lead dev skill that actually transfers is knowing which constraints to encode in the codebase itself, not in conversations. Test suites that catch design violations, folder structures that make wrong dependencies impossible, CI checks that reject patterns you'd flag in review. The developers I've seen struggle most aren't the solo coders. It's the leads who relied on verbal feedback and tribal knowledge instead of encoding decisions into the system. Their mentorship style doesn't survive the context reset.The lead dev analogy is a useful starting point, but there's a gap that makes it misleading. When you mentor a human teammate, they build context over time. You explain the architecture once, they internalize it, and next sprint they make better decisions independently. The feedback loop compounds. With AI, context resets every session. You're not building a teammate, you're onboarding a new contractor every morning. The lead dev skill that actually transfers is knowing which constraints to encode in the codebase itself, not in conversations. Test suites that catch design violations, folder structures that make wrong dependencies impossible, CI checks that reject patterns you'd flag in review. The developers I've seen struggle most aren't the solo coders. It's the leads who relied on verbal feedback and tribal knowledge instead of encoding decisions into the system. Their mentorship style doesn't survive the context reset.

Something that I think goes under-emphasized is how much AI coding demands a 'lead dev' mentality. If you spent your pre-AI career trying to level up your teammates (through API design, feedback loops, architecture) Then working with AI will feel natural. If you only focused on your own output, it will feel super bad.

@brandur Not a contradiction. - Many devs are (wisely) building on the side while retaining the "security" of a job. - Many are building quietly. - Many are not cut out to be founders. - It's too early to make this judgment. Now *IS* the best time to build.

A contradiction: Many developers (incl ones I know) are claiming 10-100x productivity gains via LLM. Almost none of them are quitting their jobs to prove it in the free market. If AI is *that* good, the time to turn founder is now isn't it? Why not take advantage of the lead?

@StealthQE4 It's already increased productivity. The only question is by how much and to what effect?

What if AI doesn’t increase productivity and just turns out to be another tech widget/fad?

@IMAO_ Software engineering is ground zero for what will eventually ripple out to the rest of knowledge work (and indirectly to all workers). For most (those in professions not yet reached by the shockwave) AI remains an amusing parlor trick. For now.

Yes, there is a lot of existential dread as what had been the safest tech job is being increasingly automated. Software engineers worry the most about AI because we work most directly with it and the disruption to us is not theoretical.

@adamwathan There has never been a better time to be a builder.

I don’t think AI is lowering the barrier to entry as much as it is giving the very smartest people an even more enormous advantage.

AI massively collapses the distance from intent to execution. Bad news for the junior-/mid-level developer. Good news for the senior-/solo developer.

Subtle flex, Claude.

Live feed of me waiting for @claudeai to come back up.

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.

@GKCdaily The rise of moral relativism, feminism, and the welfare state would like a word...

It cannot be too often repeated that what destroyed the Family in the modern world was Capitalism.

@ThePrimeagen LoC as a productivity metric only exists as a topic of engagement farmers on dev X. No serious company uses this.

hey, asking for a friend can we stop using lines of code for a measurement in productivity? at one point we all agreed on this