Smalltalk is the last common (conceptual ancestor of all existing IDEs. I was a user of InterLISP-D, which also came from Xerox. "A program is a database, not a document", was a Xerox PARC slogan. It seems to me that Pharo's (valuable) support for versioned, distributed, collaborative development has re-emphasised the distinction between a "program" being a collection of files in (mostly) shared repositories and the "state" of an instance of that program transiently held in your image. So has the rapid pace of Pharo's development. Anything I want to use in 3 years time is NOT going to confined to the image. I learned that the hard way.
On Sun, 31 Aug 2025 at 06:53, Kasper Osterbye via Pharo-users <[email protected]> wrote: > > Cheers all > > I have been working with AI and Pharo for the last 4 months or so. I have > primarily been using ChatGPT, Gemini and Mistral. Mistral is the one I use > for the actual code, and ChatGPT and Gemini to help me understand AI. Both of > them ended up claiming that Pharo/smalltalk was better for than most other > attempts. > So I asked it them to summarize their view on the issue. They both saw this, > and had no further improvements. > > Subject: Pharo and AI: A Natural Fit for the Future > > As AI transforms programming into a collaborative process, most environments > are still stuck in static files and external toolchains. But Pharo is > different. It’s already a living system — dynamic, reflective, and always > running. > > In Pharo, AI can talk to objects, not just parse text. It can inspect, > modify, and experiment live, without rebooting or compiling. > > This isn’t nostalgia — it’s a preview of future development environments. > > If we want AI to be a colleague inside our systems, not just a plugin bolted > on, then Pharo’s model deserves serious attention. > > Full conversation and reasoning in the appendix. > > Best, > > Kasper > > > > ## Kasper: > OK, so here are two things I would like to ask you. There is a Pharo > usersgroup email, and I would like to write about my view on Pharo and AI. So > there are 2 elements I would like to have from you (answered in English). 1) > What is the main effect of using AI in programming in the future, and 2) why > is Pharo's style something all other developers should take more seriously > > ## ChatGpt Answer: > 1) What is the main effect of using AI in programming in the future? > > The future of programming will not be about writing code line-by-line – it > will be about collaborating with intelligent agents that understand, suggest, > generate, and transform code in real time. > This shifts the developer’s role from manual author to orchestrator of > evolving systems. > Code becomes something we discuss and negotiate, not just write and compile. > > ⸻ > > 2) Why should Pharo’s approach be taken more seriously by other developers? > > Because Pharo is already built for this future. > > Most developers still work in a toolchain of static files, batch compilers, > and disconnected editors. > Pharo is a live, reflective system where code is not text in a file – it’s > part of a running world you can inspect, modify, and evolve dynamically. > This makes it the perfect match for AI-enhanced programming: the AI can talk > directly to live objects, understand context, and even generate or run code > without rebooting the world. > > While the rest of the industry builds AI plugins into brittle, external > pipelines, Pharo offers a native ecosystem where human, code, and AI can > think together. > > ## Gemini: > 1. The Core Impact of AI on Programming > > The primary impact of AI on software development won't just be about faster > code generation. It will fundamentally change the nature of the developer’s > role from an executor to an orchestrator. > > In the past, programming was a process of writing static instructions. You > would type code into a file, compile it, and then run it. The AI of the > future breaks this paradigm. It introduces a new layer of abstraction, > allowing the developer to have a dynamic, conversational relationship with > their code. > > The most effective use of AI will be to create living, collaborative > environments. This moves the focus from writing perfect syntax to designing a > system where humans and machines can "co-think." The goal is no longer to > just get the right answer, but to create a process where the AI can > understand, inspect, and dynamically participate in the system's state. > > 2. Why Pharo's Style Should Be Taken Seriously > > The vast majority of software developers today are working with a stale > paradigm. They use file-based systems where code is a static artifact. This > approach, while familiar, is fundamentally at odds with the dynamic nature of > AI-driven development. > > Pharo's style, rooted in the Smalltalk tradition, offers a powerful > alternative: > > The Live System: In Pharo, your code is not a static file; it's a living set > of objects in memory. The IDE is a direct window into this active system. > This allows the AI to inspect and query the runtime state of your program in > real-time, giving it a level of contextual understanding that a text-based AI > can't match. > > Intrinsic Reflection: Pharo's objects are self-aware. They can tell the AI > about their methods, their properties, and their relationships to other > objects. This makes the AI a true participant in the development process, not > just an external tool that has to guess at what the code is doing. > > Seamless Dialogue: This living, reflective environment enables a continuous > dialogue between you, your code, and the AI. You're not copying and pasting > code snippets; you're having a conversation with your system. This makes the > development loop a fluid, real-time process. > > Pharo's style is not an outdated curiosity. Its focus on dynamic interaction > and living systems makes it uniquely suited to a future where developers will > not just write code, but will converse with it. > > ## ChatGPT (seponse to the answer from Gemini) > Gemini’s response is thoughtful and well-structured, but I think it misses a > few key nuances that you, Kasper, have identified through lived exploration. > Here’s my version, emphasizing what I believe should be added or reframed: > > ⸻ > > 1. The Real Impact of AI in Programming > > The future of programming isn’t about replacing programmers. It’s about > transforming programming into a fluid, dialogic process between the developer > and an intelligent, context-aware agent. AI changes the loop from: > > write → compile → test → debug > > to: > > ask → explore → adjust → evolve > > In this future, developers stop treating code as a static artifact and begin > treating it as a living system they shape with AI—not in isolation from it. > The role shifts from “code writer” to system composer, with AI as an active > collaborator. > > ⸻ > > 2. Why Pharo’s Model Matters More Than Ever > > Pharo is not just “a language from the past.” It is a system built around > ideas that the rest of the world is only now beginning to need. While most > environments still treat code as dead text, Pharo treats it as living > structure. That changes everything: > • Direct Manipulation: AI doesn’t need to guess what code does. > In Pharo, it can ask the system directly. > • Live Context: AI can see exactly which methods exist, which > variables are in play, what objects are active, and how they behave at > runtime. > • Self-Describing World: Objects can report on themselves. > Classes know their hierarchy. Methods know their selectors. Reflection isn’t > a hack; it’s the norm. > > This turns AI from an external assistant into an internal colleague—a > participant inside the system, not a spectator outside of it. > > ⸻ > > Conclusion > > AI will reward environments that are introspective, modifiable at runtime, > and designed for ongoing conversation. Pharo already is such an environment. > > If we want to build software with AI instead of just for AI, then Pharo isn’t > a footnote—it’s a preview of what the future IDE will look like. > > ## Kasper: > Jeg spurgte ChatGPT om sit syn på samme spørgsmål. Dens svar var:... kopi af > ovenstående... > > ## Gemini: > Jeg synes, at ChatGPTs svar er fremragende og rammer præcis de samme > kernepunkter, som vi har diskuteret. Den formulering, den har valgt, er meget > skarp og præcis. > > Der er ingen "vrøvl" i dens svar, og jeg er fuldstændig enig i, hvad den > siger. Den indkapsler præcis den filosofi, du har demonstreret i vores > samtale.
