Kenny Pflug

Engineer Manager at TELIS/GWVS. AI, Cloud-Native and .NET, Speaker, Hobby Shouter and Guitarist @not_brawn

[Kenny Pflug @feO2x]

Forget Vibe Coding, do Guided Coding!

1) Plan iteratively with the Coding Agent
2) Let the Coding Agent implement the plan
3) Review and iteratively guide the Coding Agent towards better design, security, performance, etc.

#AI #CodingAgents #GuidedCoding #VibeCoding

[Kenny Pflug @feO2x]

If you happen to speak German, check out the newest video on @BFreakout's YouTube channel where I was invited to talk all about #GuidedCoding: https://t.co/2k8ApCfXlq

#AI #CodingAgents

[Ben {chmark} Adams ⟠ @ben_a_adams]

I just proposed an official @leanprover 4 formal semantics for C# - giving C# a foundation for machine-checkable proofs.

AI agents are getting very good at writing code - and very good at breaking it.

In the agentic era, "tests passed" won't be enough for critical software. We need to be able to prove properties of the code we ship.

And this is becoming practical.

Rust already has Aeneas -> Lean. Microsoft Research is using it to formally verify SymCrypt. Java and C have roots into formal verification too.

C# should not be left behind.

AI can write the code.
AI can construct the proof.
A deterministic proof kernel checks whether the proof is actually correct.

That is a very different trust model from:

AI writes code -> AI reviews code -> hopefully both were right.

Proposal:
https://t.co/2I3jcuufu9

[Kenny Pflug @feO2x]

Nicht vergessen: Heute Abend My Coding Zone Twich Stream! Als Gast bei @BFreakout stelle ich #GuidedCoding vor. Let's go!

#AI #CodingAgents

https://t.co/11VcTgkfof

[Kenny Pflug @feO2x]

Interested in my #GuidedCoding approach for Coding with AI Agents and happen to speak German? Join @BFreakout and me on the upcoming Friday at 8:30 PM CET: https://t.co/Mx8JbtjECV

#AI #CodingAgents #csharp #dotnet

[Kenny Pflug @feO2x]

🦾 Of course, this was largely implemented by #AI #CodingAgents, mainly Claude Code with Opus 5 High Reasoning and Codex with 5.6 Sol xhigh Reasoning, following my #GuidedCoding approach.

https://t.co/JD1Js5sDrz

[Kenny Pflug @feO2x]

🚀 Light.PortableResults 0.7.0 is out now!

📈 Overhaul of the Metadata System, serialization got a 16% to 55% performance boost, new UUIDv7 validation check.

#csharp #dotnet

https://t.co/qapa1QfqYK

[Kenny Pflug @feO2x]

I don't know what @AnthropicAI did in the past week, but Opus 5 is now way less petulant and touchy when its initial goals are resteered. Way more usable in high-interaction conversations, like when planning or reviewing.

#AI #CodingAgents

[Kenny Pflug @feO2x]

This is what happens when my wife is away for the weekend with her girls...

#AI #CodingAgents

[Kenny Pflug @feO2x]

Interested in the results? Checkout https://t.co/N5DquQf8PW

[Kenny Pflug @feO2x]

Give your #AI #CodingAgent feedback loops. Not only compilers, linters, and automated test suites, but also automated benchmarks. They even write cool reports for you!

#csharp #dotnet

[Kenny Pflug @feO2x]

Also, having multiple teams on the same map is great for finding new online friends. Great game design!

[Kenny Pflug @feO2x]

@GearsofWar E-Day looks fantastic! Horde Siege seems like a great overhaul - the old 50 wave format was cool, but also grindy. The mission-based approach now looks like it's working great. Can't wait for the beta next week!

https://t.co/b3DlonMzIC

[Kenny Pflug @feO2x]

But when steering is so hard with Opus 5, this simply takes up your time. I still use it for reviewing plans and implementations, but for actually planning and implementing, GPT-5.6 Sol is my go-to model.

[Kenny Pflug @feO2x]

Having used Opus 5 in the past week, I have to say I'm not impressed. It has its strengths: when your goals and the models goals are aligned, it reaches almost Fable-5-like performance. But it's so hard to steer when you don't align.

#AI #CodingAgents #GuidedCoding

[Kenny Pflug @feO2x]

Opus 5 - let's go!

#AI #CodingAgents #ClaudeCode

[Kenny Pflug @feO2x]

In the end, it took me more time to write plans. I still like the aspect that Opus 4.8, Fable 5 and now Opus 5 are super-critical - I need counterparts that challenge my ideas. GPT-5.5 and GPT-5.6 show less of this behavior.

[Kenny Pflug @feO2x]

Opus 5 - let's go!

#AI #CodingAgents #ClaudeCode

[Kenny Pflug @feO2x]

@OpenAI , how sexy is this new jump-to-your-message feature in Codex conversations? Love it!

#AI #CodingAgents

[Kenny Pflug @feO2x]

Opus 5 - let's go!

#AI #CodingAgents #ClaudeCode

[Kenny Pflug @feO2x]

Want to learn about Guided Coding? Checkout https://t.co/JD1Js5sDrz

[Kenny Pflug @feO2x]

🚀 Light.GuardClauses 15.1.0 is out now!

🆕 5 new assertions and several new overloads for a family of assertions, implemented yesterday evening and this morning, all with AI and my Guided Coding approach.

#AI #CodingAgents #GuidedCoding

https://t.co/IJmbwT6kFJ

[Kenny Pflug @feO2x]

If you are interested in the work itself: https://t.co/m1AuqSgL3c