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

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

We need to tell the ‘good vibes’ from the ‘bad’ ones. #Neurosymbolic paradigms are of paramount importance. #Agentic coding is also not the ‘ozempic of labor costs’ either - smart companies will keep their (skilled) staff get more stuff done and expand #JevonsParadox #SAP #ABAP
2/2

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

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

As auto-regressive token predictors #LLM predict syntax patterns and have zero senantic understanding:
esolang-bench.vercel...
#SAP #ABAP

Formal abstractions and not natural language are the lingua franca of #science and consequently of #intelligence.
2/2

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

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

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

Languages like #prolog #ocaml #lisp which are much better suited for #AI will potentially have a huge revival with the advent of #tensorlogic and #textdiffusion models
2/2

#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

@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.

In #SAP the notoriously slow transport times ‘drag’ #agentic #coding.We should abandon 3-system landscapes and use 2-system ones - dev and prod with a dedicated test client in dev with good data which will significantly improve performance becaus the agent generates and tests in dev only #ABAP
2/2

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

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

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

#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

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!🚨🔥

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

Consequently, agentic coding underperforms in languages like #Haskell and #Prolog for architectural reasons and not only because of comparably sparse training data. With the advent of #tensorlogic where predicative logic runs on learnable tensors that could be a serious problem. #AI
2/2

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

#TensorLogic also means that #declarativeprogramming and #functionalprogramming might have a huge boost from this. Anybody motivated to write a lightning fast and hyper-scalable #Prolog on #CUDA and some torch lib? 👍
#Lisp #Coalton #OCaml
2/2

#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

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

#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’

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

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

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

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