State of AI coding 11/2026

What happens in this year: 

1. AI coding is going full throttle, the first stage of experimenting is over
2. The amount of code is growing faster, code generation is accelerating
3. Cheaper code finds the way to "less important" fields like mining, construction, health care and agriculture 

Finally Prediction 2027:

1. The accelerated code generation will go on in 2027
2. Invest in good software developer/people/teams or you will drown in AI slope 
3. Efficiency in AI usage will slowly become more important

TL;DR 

Primary base of this article is Octoverse by github. 

Early this year I ask my co-workers about the future of software development. And mostly every body had a complete different view on it. What I will do here is to explain the views in to opposite visions, maybe a "little bit" exaggerated.

Vision 1: Doom 

We are doomed, as the most extreme future vision or more specific, all developers will losing there jobs.

The idea: AI does all the coding/all work. We will lose out jobs, we will losing every thing ...  

Vision 2: Star Trek 

Based on experiences different from our past, AI will lower the cost of software production this enables software to go into more areas then before. Let me give some examples from the past.

ATMs free tellers from there job but today there are working more people in the banks. They are doing more high level jobs. Banks growing since.

Electronic calculator, math teachers feel threaten by the affordable electronic calculators (1986, USA). Still today math is an important skill and math teachers are needed. Electronic calculators enables us to do more complex math, faster.

Computer, Howard Aiken estimate that a handful of computer are needed for the US's needs. Today, my light switch contains a computer. Computers and software is everywhere.

Excel or more precise Visicalc (1979) or earlier Mainframes frees people from the human computing department. Since spread sheet software, we are doing a lot more calculations and simulations then ever.

What I show you is called the rebound effect, make something cheaper then we are using a lot more. I believe that this rebound effect will kick in and the AI will free us to create more software, a lot more.

Octoverse 

As I read the Octoversetext, I see sign that fits into the 'Star Trek' vision. The LOC (commits) explodes. Software getting much much stronger in strange fields like mining. 

AI free many so called junior developers, often with a only a 3 or 6 month training. These people are need in more sophisticated positions. Why, there a more software to build.

Prepare for Warp speed. Fasten your seat belt, the software starship leaves the dockyard, now.

 

Orbit

Substantiv: Orbit, Umlaufbahn, Umlauf, Kreisbahn, Augenhöhle, Kreis, Umkreisung, Flugbahn, Bereich, Machtbereich, Einflussphäre
Verb: umkreisen, kreisen, umlaufen

The 6th finger of agentic software development

 Every body knows AI generated images with people with six fingers or three arm. But there is also a 6th finger in agentic programming, AI overdue most tasks. AI writes to much code. AI is not able to reuse exiting code in a simple way. AI increases code volume (LOC) and complexity.

 

The big question: Is the increasing code complexity still a problem? Because we have AI.

Yes, yes:

AI acts like an Junior developer. The permanent (tendency) adding of code and complexity and the inability of simplification will lead to an unmaintainable, unstable, in-secure software system. Like always. This point in only further away.

AI makes software development not easier. AI makes coding easier. This is the reason why excellent teams accelerate and bad teams struggle so much using AI.

AI slope is waiting for me.

 

 

PS: 

AI makes coding easier, but not for all programming languages in the same way. AI is good in Python, JavaScript, HTML and Java. All these languages have huge trainings set.

 

Diffenrent Level of coding with AI

 Important notice, if you want to code with AI at one of the levels, you must master all lower levels, there is no short cut. If you want Level 4 multi agent coding, you must go through Level 0, Level 1, Level2 and Level 3.

Second notice, You only reduce the coding time but software development is a little bit more, maybe around 60-80% more. 

Last remark, all values in the table are good guesses based on my experiences. 

 So, now you have to find your sweet spot.

Level	AI usage	Source code control	AI cost	AI Gain
0	no	full	no	No AI slope debugging
1	auto completion	full	no	minimal
2	prompt	full to most	non to minimal	significant reduces search time
3	agent coding	less to non	yes	coding time significant reduced
4	multiple agents	no	significant	coding time reduced to the half

 

AI assisted software development

Overall: now in 2026 software development works pretty well under some conditions:

1.  High quality code base
2.  High experienced software developers

This is the perfect combination for successful AI assisted software development. AI is getting faster and tools getting better, it's a lot of fun to code with AI. At the moment AI is in the storming phase.

You want an example, here it is a small Golf trainings app with mostly complete AI generated frontend and AI maintained and extended backend. 

 

http://golf.ebert-p.com/

Used AI:

1. aider, ollama, qwen-coder (different versions) - running local models
2. grok build beta 

 

Bullshit Asymmetry in Software Development or Why is Software recunstructing so expensive

Bullshit Asymmetry in Software Development means that is very easy to develop a new system on a green field. You can easily go on putting new features into the code  but over time, often faster then slower, you have to put more and more effort to add new features until you reached the culminating point. At the software development culminating point your resources (developers) are exhausted, no new feature can be implemented in acceptable time. Next the development team is wearing out and then I'm appearing.

1.  Software reconstructing is more expensive then writing the software. The costs are asymmetric. Build a new software is much cheaper then reconstruction/rescuing legacy software. 
2. But software reconstructing lowers the risk of a complete miss. The improvements are coming at a constant speed. No new teams are needed. Reconstructing software can be realized by the origin team, maybe extended by some external experts. 

 There is a third way, re-implementation of an existing system. This way combines low risks, like software reconstruction with the low costs of building a new software.

  

	Write new software	Reconstructing software	Re-implementation
cost	low	high	low
risk	high	low	low
results	after long time	immediately, slow flow of improvements	after not so long time
team	new team needed + one insider	existing team + some external experts	Only some seniors needed
new features	are implemented	slow but steady, accelerating	no, but faster after release

Easy Ways to increase efficiency in software companies: Meetings

 

The efficiency in many software companies are low. You may know it, endless meetings with to much people never needed. Presence counts more then results. But here some simple things that increasing the efficiency are really easy to implement:

1. One meeting free day a week (Meeting-frei Freitag)
2. No back to back meetings, at least 5 min break between
3. Time boxed meetings
4. Regular breaks in long meetings 

This ideas will not fix every thing but they are simple and easy to implement. And these ideas could be a turning point to more focused, result focused work. 

 

Fun fact, after introducing a meeting free Friday, after some time, a lot of meetings appears on the meeting free Friday, because there was a lot of free time. But now the Thursday is now meeting free.