Ingmar Krusch

proud dad, techie, passionate about empowering & growing people

[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.

[Ingmar Krusch @IngmarKrusch]

Have you started to use GH Copilot in your dev teams? What are your experiences? Is it already value adding to roll it out to your tech org? Do you still consider it a "toy" at this point?

Would love to hear your thoughts as I am contemplating wether to introduce this or not.

[Julia MacDonald @julia_m_mac]

McKinsey is paid to solve complex problems.

They created a process that helps find solutions:

The Hypothesis-Driven Framework.

Let’s dive in.👇

[Anonymous @LatestAnonPress]

⚠️ If you're in #Ukraine and reading this please turn geolocation off on your phone now. Russia is using it to track gatherings. Tell those around you to do the same.

[Ingmar Krusch @IngmarKrusch]

You build it, you own it is how you can build quickly but still be able to maintain many services in quality at scale. Join me on @Clubhouse at 16:00 CEST on June 24th to learn about the engineering culture @Solarisbank -> join here https://t.co/McYD2Ryol5

[Satyajit Ranjeev @sat_ran]

The fancy way of writing this sucked. May be this works. I'm looking for #softwareengineers who will help me build systems @solarisbank that power the banking platform for the likes of SamsungPay. What I can offer is autonomy and an environment to grow. DM if interested. #golang

[Ingmar Krusch @IngmarKrusch]

@sat_ran :D that and it reminds me of the Stockholm-Syndrom ;)

[Ingmar Krusch @IngmarKrusch]

@bjrnsblg Ya and we deploy 180 times a week. Reduces risk, auditors like that if you explain that properly 😎

[Solaris @solaris_se]

solarisBank's Deputy VP of TechOps @stpn108 and VP of Engineering @IngmarKrusch were up on the big stage today at #PDConnectBerlin to explain how to scale smartly and swiftly in regulated environments🚀
Missed the talk? Check out the pics below 📸

[Ingmar Krusch @IngmarKrusch]

Join me & @stpn108 at PagerDuty Connect Berlin on Nov 12th where we talk about how @solarisBank enables banking-as-a-service with lightning speed.
Find out how leading orgs run digital operations & incident management #connectberlin #pagerduty #digitalops https://t.co/M0wB4o21vV

[DevOpsDays Berlin @blndevops]

DevOpsDays are nothing without its audience! Register now and be part! https://t.co/VcaGDsjY0S #devopsdays

[Stefano Zanella @stefano_zanella]

I'm extremely proud to announce that this year @solarisBank is a diversity sponsor at @ElixirConfEU 🎉

I'll be there: if you're around and want to talk about #Elixir, #diversity or #tech in general feel free to reach out, I'll be happy to share a coffee with you!

[Ingmar Krusch @IngmarKrusch]

@5nafu Der Vergleich hinkt, ist ja nicht der Privatrechner des Kollegens.

[Jörg Howein @J_Howein]

Whenever I stumble across it again: makes even more sense with every other read! #Banking #Context ⁦@solarisBank⁩ https://t.co/pEMZ0oDFRe

[Solaris @solaris_se]

Our Core Banking team is responsible for building, modifying and optimizing a large part of the #techarchitecture on our #bankingplatform. Get an introduction to how #CoreBanking works at solarisBank on our blog post. https://t.co/lvR5bfntRY

[DevOpsDays Berlin @blndevops]

The (preliminary) program for DevOpsDays Berlin 2018 is online! Lots of great talks, ignites and workshops by awesome speakers. This is the time to register for the conference!
https://t.co/IA7InKB2uj

[Solaris @solaris_se]

Our Jens Herrmann will give a talk on "Using @concourseci in a highly regulated environment" at @blndevops meetup, July 12th @NI_News's Berlin office! It will give you an impression on how we #buildComplianceIn, and how we strive to #AutomateAllThings https://t.co/yllrVIlqKy

[Solaris @solaris_se]

We're truly excited to launch our own @solarisBank Blockchain Factory today to become the #banking partner for the #cryptocurrency and #blockchain industry. Read more about this strategic step in our official press release:
https://t.co/EG2qiqopZG

[Solaris @solaris_se]

"Interestingly, many of these pioneers face exactly the same problem fintechs were facing three years ago: The need of a licensed partner." CTO & #blockchain lead @peterlih wrote a @Medium article on why we launched the @solarisBank Blockchain Factory https://t.co/QfdipRpGZa

[DevOpsDays Berlin @blndevops]

#DevOpsDays #Berlin aims to be - as all #DevOpsDays - a diverse conference. But we need your active help with that. The results for our CfP so far show a clear underrepresentation of female speakers. Get active and change this until June 30th! https://t.co/ZyAt8fauDX