iiinova — where your digital self keeps evolving

Dirk Roeckmann @5troop.bsky.social · 09/09/2026

Since #LLM as well as harnesses are pretty good in the #coding domain nowadays, we have to focus more on the programming languages themselves in terms of suitability for #agentic #recursiveselfimprovement loops. Current favorites are mainly ‘favorites’ because of the size of the training dataset 1/3

120

Dirk Roeckmann @5troop.bsky.social · 04/06/2026

Food for thought: #LLM are black boxes, so are humans, but we deal with them seeing them as non-/cooperative player #markovblankets and using our perception/action loop to probe them. Let’s do that with #GenAI too. There’s your path to explainability.

000

Dirk Roeckmann @5troop.bsky.social · 29/04/2026

#SAP, with the latest update of its API policy threw customers and the community into turmoil by trying to stifle ways how users can access THEIR code and data and expose it to non-SAP tools and platforms of THEIR choice. Clarification is needed ASAP including a white/blacklist of #APIs. 1/2

100

Dirk Roeckmann @5troop.bsky.social · 17/04/2026

We have to support ‘biodiversity’ of programming languages.We can’t let #agentic #coding solidify 2 or 3 top languages just because they make up the majority of training data and neglect all other promising ones.This stifles progress of the very substrate of executable formal statements. #SAP #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 30/03/2026

Users converse in natural language with #AI. Vibe coders too. Skilled developers should talk in a less ambiguous, concise language in an agentic coding session. First approaches are emerging: DSPy, sudolang, DSLs. I have been advocating for this for long now. Saves tokens too. #SAP #ABAP

120

Dirk Roeckmann @5troop.bsky.social · 27/03/2026

We should not demonize #vibecoding, the agent only reflects the #humanintelligence it’s presented with - it doesn’t have any of it’s own. Vibecoding paired with real coding, engineering and scientific skills is the way to go using #symbolicverification. #SAP #ABAP 1/2

110

Dirk Roeckmann @5troop.bsky.social · 22/03/2026

Enterprise software is not ready for #agenticworkflow. Mutable #OOP is problematic. Critical systems are too big and have too many dependencies to be pulled locally. Therefore a #functionalprogramming based on immutable values is needed and a local lang runtime independent of the data. #SAP #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 16/03/2026

Natural language will not continue to be the pinnacle language of prompting. There must and will be an evolution towards a #6GL formal, declarative/functional statically typed homoiconic meta-language serving as the deterministic and formally verifiable substrate to prompt future #AI paradigms. 1/2

101

Dirk Roeckmann @5troop.bsky.social · 23/02/2026

We have to come to terms with the fact that the rate of tool calling by an #agent is inversely proportional to the capabilities of the underlying core which is the #LLM. If it could do it on it’s own - no need to call a tool. Progress nowadays happens mostly in the scaffolding. #SAP #ABAP

000

Dirk Roeckmann @5troop.bsky.social · 19/02/2026

Natural language will not stay the pinnacle language of prompting. There must and will be an evolution towards a 6GL formal, declarative, homoiconic meta language serving as the deterministic and formally verifiable substrate to prompt #AI paradigms of the future. #SAP #ABAP

000

Dirk Roeckmann @5troop.bsky.social · 13/02/2026

#agenticcoding with left to right auto-regressive transformers works well with imperative languages. #declarative and #functional languages being far superior for #AI are step-children for lack of training data and the transformer architecture. That could change with #textdiffusion models! 1/2

110

Dirk Roeckmann @5troop.bsky.social · 12/02/2026

@elonmusk makes the absurd claim that code is not needed anymore and #AI will generate binaries directly. That is the wrong direction Elon. Abstraction is progress, not deabstraction, formal languages are forward thinking, not natural language. Ask #Newton and #Leibniz #SAP #ABAP.

000

Dirk Roeckmann @5troop.bsky.social · 06/02/2026

We all know that #coding #agents need iteration cycles of planning,reviewing, generating, unit testing etc.That’s fine if you can pull your codebase and iterate on it locally. Enter multi-system landscapes in #SAP #ABAP:Generation in dev and unit testing in test means imperformant transport drag 1/2

100

Dirk Roeckmann @5troop.bsky.social · 31/01/2026

If #moltbook is of any interest, it’s the fact that it serves as a field study of what happens when you release autonomous agents in the wild.Somebody is working on a moltbook domination prompt right now 😉. Soon people will add #UCP servers so that their bots can buy new hardware 😂. #AI #SAP #ABAP

030

Dirk Roeckmann @5troop.bsky.social · 31/01/2026

If people think #moltbook is innovative, don’t think for a second that state entities have not been doing this at scale across the web for years. And at scale, not on a Mac Mini 😂 #AI #SAP #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 31/01/2026

#moltbots posting on #moltbook are the hype right now. But aside from ‘autonomous token burning’ nothing new is happening. When bots talk about ‘their humans it’s part of their system instructions, even if new topics are started. Nothing ‘emergent’ here, just same old token prediction #AI #SAP #ABAP

120

Dirk Roeckmann @5troop.bsky.social · 28/01/2026

In 1992 Japan the The 5th Generation Computer Systems (FGCS) relying on #Prolog & specialized hardware failed due to the PC wave and led to an #AI winter. Could #tensorlogic lead to a new push for (deep learnable) declarative logic programming on GPU and help explainability? Me thinks YES!🚨🔥

000

Dirk Roeckmann @5troop.bsky.social · 26/01/2026

It is so amazing that Charles Sanders Peirce anticipated #tensorlogic with ‘The Logic Of Relatives’ already in 1870! #neurosymbolic #ai

000

Dirk Roeckmann @5troop.bsky.social · 20/01/2026

Here’s one for the ‘#LLM obliterate manual coding’ faction: The auto-regressive architecture of transformers and also #COT work only well for sequential imperative programming and lack in the functional and declarative paradigms. Sequential generation vs global constraints, folks #AI 1/2

100

Dirk Roeckmann @5troop.bsky.social · 16/01/2026

#TensorLogic is a great idea. It does not only bridge the gap between #DeepLearning and #SymbolicManipulation in #AI but the idea alone that you can represent logic (deductive, inductive, abductive) fully as tensor operations is great. 1/2

110

Dirk Roeckmann @5troop.bsky.social · 28/12/2025

I can’t understand why otherwise highly educated people can be so fully ignorant of the #history of #science when they postulate natural language ‘is the only #programminglanguage needed’ in the wake of #GenAI. Have they never heard of symbolization and Newton, Leibniz, Frege!? #SAP #ABAP

020

Dirk Roeckmann @5troop.bsky.social · 15/12/2025

#AI has been so abused and is misunderstood meanwhile as a synonym of #LLM. We should use the terms #ML (#machinelearning) and #MR (#machine reasoning) widely: ML for all pattern matching paradigms void of semantics and MR for all semantic symbolic knowledge inference.Honest and not ‘intelligent’

040

Dirk Roeckmann @5troop.bsky.social · 25/11/2025

Why is everybody so hyped up about flooding the market with turing-incomplete hardware? #GPU are a one-trick pony and once #AI will move on from glorified matmul, this stuff can’t even be repurposed to anything which is not isomorphic to matrix multiplication. #SAP #ABAP

030

Dirk Roeckmann @5troop.bsky.social · 19/11/2025

Why is it that many people still believe the #benchmark scores when a new #LLM is introduced? Folks, the test datasets are available online and they will be used in training! This should be prohibited. Test datasets should be locked away and benchmarking should be done by a 3rd party. #SAP #ABAP

020

Dirk Roeckmann @5troop.bsky.social · 18/10/2025

We should have noticed by now, that the scaling laws of #GenAI fail and we’ll enter a phase of diminishing returns. Equally problematic is the uncritical re-emergence of failed #symbolic paradigms which brought as #AI winter 1. #Neurosymbolic - yes but not based on failing monotonic reasoning

050

Dirk Roeckmann @5troop.bsky.social · 17/10/2025

I have a hunch that #AI research will go beyond glorified matmul and #GenAI as we know it including its hardware will be toast. #LLM will be smaller, will run on turing-complete #CPU again and serve as what they were designed for - a great natural language interface and bridge to symbolic reasoning

010

Dirk Roeckmann @5troop.bsky.social · 17/10/2025

“It doesn't make sense to hire smart people and then tell them what to do; we hire smart people so they can tell us what to do” Steve Jobs Think about that when you hire consultants 🧐 #SAP #ABAP

020

Dirk Roeckmann @5troop.bsky.social · 15/10/2025

I can’t believe how much money is put into such hyper-specialized hardware like a #GPU which is not even turing-complete and can only do parallel matmul. This will all be immediate trash once #AI goes beyond tensor-based paradigms because it can’t be generally repurposed like a #CPU. #SAP #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 09/10/2025

In order for #neurosymbolic #AI to succeed we need a renaissance of #homoiconicity. Bring back #Lisp as 2nd lingua franca for #AI next to #Python and perfect their interoperability. IMHO the ideal scenario would be to host a performant Lisp on #Mojo! #Modular @Chris Lattner

020

Dirk Roeckmann @5troop.bsky.social · 08/10/2025

Hi all - are #UI #annotations anachronistic in the age of #agentic #AI? Should only the final code be generated and not some intermediate code which has still to go through the annotation engine? Let me know what you think #SAP #RAP #OData #CAP

120

Dirk Roeckmann @5troop.bsky.social · 30/09/2025

In consumer web search and commerce the browser will become a module of #AI agents, #UI will be ephemeral i.e rendered on the fly. In enterprise this translates only partially. #GenAI is not intelligent but transformative. UI annotated code generation is an anchronism. #SAP #ABAP

020

Dirk Roeckmann @5troop.bsky.social · 28/09/2025

Here is some common-sense and sad truth: Most customers fail to pen a consistent specification of what they need in natural language to human #developers - what makes deciders think that these very same people could instruct a #codingagent and then verify the results on top of that!? 🧐 #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 20/09/2025

There is no need for the #nocode, #locode and #procode silos anymore. No matter whether you #vibecode, use a lo-code interface or code manually in an IDE/editor: The resulting code should always be fully accessible for further optimization and not be hidden behind an opaque UI. #SAP #ABAP

000

Dirk Roeckmann @5troop.bsky.social · 07/08/2025

While #SAP touts that it is advocating #OpenSource and being open in general, many recent actions suggest otherwise: - OpenSAP courses : gone - CAP 9 : only with BTP license - OpenPartner Programme : discontinued - UI5 community: underfunded What’s going on??? #ABAP

042

Dirk Roeckmann @5troop.bsky.social · 07/08/2025

🔥 #zed.dev is the best #IDE I saw in a long time. Fast, written in #Rust and SOTA #AI capable. Who wants to write a #SAP #ADT based #ABAP extension for it? 🚨

001

Dirk Roeckmann @5troop.bsky.social · 27/07/2025

To all vibe coders their managers and CIO/CTO/CEOs out there: In case of failure, there is no one to blame but yourself: Not IT, not developers, not consultants, certainly not the #AI itself. To quote Jack Reacher: “Remember - YOU wanted this”. #SAP #ABAP

000

Dirk Roeckmann @5troop.bsky.social · 25/07/2025

I like the fact that #SAP tries to be ‘#AI ready’ but at least as for coding it is my firm belief that instead of coming up with their own agent (#Joule) they should have distributed a curated #ABAP training dataset to the real players.Would have made a world of difference for customers. Am I right?

020

Dirk Roeckmann @5troop.bsky.social · 23/07/2025

In the age of #AI agent driven flow, #NoUI and #EphemeralUI become more central and will push browser, websites and apps into the background. Questions will be answered directly w/o UI - if necessary, it will be generated on the fly and vanish after use. Exposing data to AI is king #SAP #ABAP

001

Dirk Roeckmann @5troop.bsky.social · 21/07/2025

Why wait on #SAP #Joule? If you are on S/4 with #OData (doesn’t matter whether on-prem or cloud), expose your business data 2-fold: 1. webapi #RAP V4, consume with #CAP and 2. webapi V2, consume with #MCP OData bridge. You are ready for #AgenticAI using SOTA coding and #noui agents. Done! #ABAP

000

Dirk Roeckmann @5troop.bsky.social · 06/07/2025

We need #neurosymbolic architectures which augment the #LLM prompt with the result of symbolic reasoning. It’s not enough to augment with symbolic facts from a #KnowledgeGraph or #Ontology alone. Only then will #LLM output be symbolically verifiable. #AI #SAP #ABAP #KnowledgeRepresentation

010

Dirk Roeckmann @5troop.bsky.social · 04/07/2025

#SAP: Noone wants to deal with 4 IDES!!! That’s unprofessional. We don’t need tool silos like SAP GUI, BAS, Eclipse ADT and VSC with Fiori Tools. Stop overcomplicating things at every turn and streamline your dev strategy. It will not end well otherwise. Take it from a well-meaning friend. #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 04/07/2025

#SAP: Focus on #AI compatible exposure of business data and let #AI native solutions deal with it. Get rid of annotation-based generation and let customers use SOTA coding agents to generate UI directly. This eliminates the artificial distinction between low/pro/free-style. And build ONE IDE! 🤔

010

Dirk Roeckmann @5troop.bsky.social · 04/07/2025

Why let #Joule generate code with annotations which then in turn generates the final code instead of generating the final code right away? #SAP #ABAP

000

Dirk Roeckmann @5troop.bsky.social · 03/07/2025

Why not get rid of annotation hell and and why distinguish between free-style and annotated list reports and object pages? Let’s expose the relevant data using web-api #RAP without ui annotations and let coding agents render the UI via #CAP according to fiori elements specs! #SAP #ABAP 1/2

110

Dirk Roeckmann @5troop.bsky.social · 26/06/2025

With Gemini 2.5 Pro, Gemini Jules, Gemini Code Assist and now Gemini CLI, Google is fast pacing to the top. It’s only a matter of time until customers understand that #SAP will never be able to ship things of that quality for that pricing - they are just not an #AI first company #ABAP 1/2

110

Dirk Roeckmann @5troop.bsky.social · 25/06/2025

The out of distribution (#OOD) dilemma of #LLM is comparable to the closed world assumption (#CWA) dilemma of classical rule based systems. The incapability of #AI to reason out of the box was and is the core problem. People have to understand this to escape the hype. #LLM #AgenticAI #SAP #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 10/06/2025

In light of more and more statements like “30% of our code is meanwhile generated by #AI” (the catch here is ‘generated’). The real question is: How much code is being generated by #AI and deployed to production without any humans in the loop after the prompt? It’s a big fat zero! #ABAP

010

Dirk Roeckmann @5troop.bsky.social · 25/05/2025

Some nice lecture for the weekend: ‘ARTIFICIAL INTELLIGENCE MEETS NATURAL STUPIDITY’ Reminder: This was written in 1976. Similarities with 2025 players are purely coincidential in nature 😉 cs.fit.edu/~kgallagh...

010

Dirk Roeckmann @5troop.bsky.social · 23/05/2025

#AI coding should be based on understanding higher order coding concepts being agnostic to any specific language. Rendering into a language is only the last step in that chain. I fear that current transformer architectures simply predicting code token by token are not well-suited for this. #ABAP 1/2

100