John Calso

Building @orchard_robots 🍎🍇🍒🫐

[John Calso @john_calso_]

@thebrunchguy @AnthropicAI Congrats!

[John Calso @john_calso_]

My flex for this week is helping an apple grower get data in time to apply a precision spray of their most expensive chemical of the season

Anytime time it rains when flowers are open they have ~24 hr window to act to prevent disease

[Y Combinator @ycombinator]

AI for Low-Pesticide Agriculture
@garrytan

Farmers are stuck in a bad loop: use more chemicals, get diminishing results, pay more, take on more risk. And they can't just stop, because if pests win, crops die.

AI that can identify individual weeds in real time, robotics that can treat one plant instead of blanketing a field, and new biological solutions mean this problem finally looks solvable.

[Charlie Wu @charliewu]

Just gave a talk at a table grape conference 🍇

3/10 farmers I met use Claude Cowork daily.

> “Claude might be able to replace my accountant or secretary, but your AI (@orchard_robots) is the only thing I’ve seen that will actually change the way I farm.”

[John Calso @john_calso_]

The rite of passage for every AI chat tool

[John Calso @john_calso_]

Lot's of room to run in Ag. It is still incredibly early

[Andrew Curran @AndrewCurran_]

Striking image from the new Anthropic labor market impact report.

[John Calso @john_calso_]

Counter: UI work is much more than mindlessly tweaking CSS.

If you work on UI, it’s on you to prove to the user that the work of everyone else in your organization - Sales, DevOps, Backend, etc. - was worth it

I oddly equate it to being an NFL kicker.

The defense worked hard to get the ball back, the offense grinded to get you into a position of opportunity. It’s up to you to determine if all of that work translates to something meaningful on the scoreboard

[ThePrimeagen @ThePrimeagen]

I have been thinking about this a lot.

I think for a great many of engineers, the ones who did it because they loved it only to discover that money was in fact at the end of the rainbow found both the journey and the destination satisfying. In fact, I think I can argue with authority that the destination was only satisfying as the journey was difficult. The hard-fought evenings spent toiling away on an idea and codebase that slowly gives way to your vision was an incredible experience.

The group of people that fell into this category of hard-fought journey and destination we will call them tinkerers. One thing tinkerers have always hated is the already known problems. The journey is clear as day. The obstacles minor inconveniences. Its purely a matter of typing the solution into the terminal. This is also why I think so many of this group goes out and does open source, or starts companies. Work largely falls into this category with few exceptions.

From this reason is why I largely find UI work soul sucking. I know the solution, its a matter of just looking up the details and putting it into my editor. yawn. CSS, flex box this, grid that, put the tailwind classes in the bag.

To me, the LLM software world is with little to no journey and discovery. Its more of simply taking my high level idea and just formulating it into testable, atomic chunks that can be verified. I have traded my favorite part, discovery and raw creation, with itemized list of TODOs and patience and "No Mistakes."

To this, every morning from 6 to 9 I simply just hand code every thin. even UI things. It is because I want journey and discovery and raw creation. Maybe one day comes and its just so futile that I stop this. But for now, I still see such great value in this. I see such better thought through products. Because slowing down and truly thinking through everything. The architecture, the design, everything is an expression of discovery and creation. And I love it.

I am sure there will come a day, maybe even in the next 6 months where I change my mind. For now, I pursue the love of the game intentionally.

I do also believe that there exists people who get the same joy I got from building with tears and sweat by prompting LLMs. I am positive of it. I just don't understand how. But people love UI work. I also don't understand that.

[John Calso @john_calso_]

@HarryStebbings @cura_inc by @sharanjhangiani is building this already

[John Calso @john_calso_]

@sharanjhangiani @linear An agent that can analyze the semantics of breadcrumbs by user, call it Hansel (or Gretel)

[TBPN @tbpn]

In an effort to expand awareness of technology and business, we bought a Super Bowl ad.

See you Sunday on NBC

[John Calso @john_calso_]

I'd like to coin the term `PRmageddon`, for when everyone has parallel agents creating a deluge of PRs but still need manual review to avoid a Slopacolypse

[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.

[John Calso @john_calso_]

@shaoruu @cursor_ai Better yet:
https://t.co/aiG7UYstk7

[John Calso @john_calso_]

@sharanjhangiani

[John Calso @john_calso_]

I feel this deeply even with only two parallel agents.

It kind of feels like cooking; you got multiple things to manage - preheating/marinating/chopping/frying, and you enter a very satisfying flow state for some time.

Afterwards, I’m absolutely wiped.

Luckily, I do think that context switching quickly & effectively can be trained with reps like a muscle

[Dominik Tornow @DominikTornow]

Unexpected effect of coding with agents: I can work on 5 things at once, but I’m completely fried by 11am.

My cognitive load isn’t reduced but compressed. Anybody else?!

[John Calso @john_calso_]

2nd annual stress test in ‘John’s heat testing facility’

a.k.a. sauna time with camera v16.5.3

Thankfully no one else stepped in and I didn’t have to explain what the heck I’m doing

[John Calso @john_calso_]

Right off the bat, the Claude Code agent experience is better, faster, and cheaper

Cursor might be turning into a glorified code review & refactoring UI

[John Calso @john_calso_]

Take time off for the holidays and all of a sudden I’m gutting my previous local dev workflows

Usually I try to be cognizant of shiny object syndrome, but when the creator of Claude Code feels behind, it’s time to catch up and reevaluate

Documenting this mostly for my future self to look back on & chuckle

[Boris Cherny @bcherny]

I feel this way most weeks tbh. Sometimes I start approaching a problem manually, and have to remind myself “claude can probably do this”. Recently we were debugging a memory leak in Claude Code, and I started approaching it the old fashioned way: connecting a profiler, using the app, pausing the profiler, manually looking through heap allocations. My coworker was looking at the same issue, and just asked Claude to make a heap dump, then read the dump to look for retained objects that probably shouldn’t be there; Claude 1-shotted it and put up a PR. The same thing happens most weeks.

In a way, newer coworkers and even new grads that don’t make all sorts of assumptions about what the model can and can’t do — legacy memories formed when using old models — are able to use the model most effectively. It takes significant mental work to re-adjust to what the model can do every month or two, as models continue to become better and better at coding and engineering.

The last month was my first month as an engineer that I didn’t open an IDE at all. Opus 4.5 wrote around 200 PRs, every single line. Software engineering is radically changing, and the hardest part even for early adopters and practitioners like us is to continue to re-adjust our expectations. And this is *still* just the beginning.

[John Calso @john_calso_]

2026 will be a year full of ‘Why?’

Funnily enough, the first release of Chat-GPT will turn 4 next year, the same age kids start their “why” phase

[Jaya Gupta @JayaGup10]

https://t.co/uPXcTUEsnc

[John Calso @john_calso_]

Definitive proof that flowering -> early fruit stage is the most hectic time of the season

[John Calso @john_calso_]

The US Apple Industry is in the midst of an oversupply problem.

Last week, I listened to an industry analyst tell a room full of growers that supply needs to drop ~12% in order to keep prices reasonable, whether by ripping out existing acreage or harvesting only top-quality fruit.

The question is: who wants to go first?

This past season, the USDA committed $35 million to purchase the surplus as a temporary measure.

It will be interesting to see how the game theory plays out over the course of next season.