26.0502 I asked GPT/Claude/Cursor to give me an improved version of the “the future” page. Just as a test. This is what I got. I would rank the replies from best to worst as

  • Claude (Sonnet 4.6) (best, by far). Seems Claude is the best for such tasks by far.
  • GPT 5.3. Redid the style to something I think is hard to read. Typical overwhelmingly verbose GPT style.
  • Cursor (one of GPT5.5, Codex 5.3, Sonnet 4.6, Opus 4.7). Total failure. A mess. Cursor seems to be quite weak at such tasks.

PS: Claude also copies flawlessly into Substack. I am not a fan of Antrophic the company, but must grudgingly admit they are in the lead in certain areas.


0 ORIGINAL =========================


1 The past, the future

50 years ago, nobody imagined PC’s (back then Commodore, Atari, etc) would change the world. In the ARPANET days we could never have imagined home internet or the search engine. The very idea that one day we could simply from the comfort of home have the ability to access what we access now was unfathomable.

How AI will change our world will undoubtedly be something we have not yet even imagined. AI IDE’s and tools will become so reliable and easy to use that the general public will be able to create sophisticated AI apps (perhaps by just chatting with an AI IDE). The goal of this page (WIP) is to suggest where things might lead.


2 Alex Karp’s “physical world” prediction

GEMINI: Palantir CEO Alex Karp has argued that AI will spark a “blue-collar revolution” rather than widespread unemployment for skilled trades, suggesting that vocational, hands-on jobs are more secure than many white-collar roles. His key points regarding blue-collar jobs in the AI era include:

  • Increased Value for Skilled Trades: Karp argues that jobs requiring physical labor and troubleshooting —such as electricians, plumbers, and mechanics— will become more valuable, not less.
  • The “Physical World” Moat: Unlike routine white-collar tasks, blue-collar work involves navigating complex, real-world conditions that are difficult to automate.
  • AI as a “Superpower”: Rather than replacing workers, AI will provide skilled labor workers with tools that enhance their productivity.
  • Rising Wages: Karp has indicated that the re-industrialization of America driven by AI will increase demand for labor, leading to higher salaries for blue-collar workers. Karp’s stance is that the future of work lies in combining AI technology with physical, vocational skills, rather than in purely intellectual or office-based jobs.


3 AI will enable the “physical world”? Remove barriers?

Imagine the near future, creating complex apps by having discussions with AI tools. Tools that drastically reduce the complexities of life (especially the man-made ones). Making it possible for us to accomplish things that seem out of reach. AI will bring us together (even more). Just as the internet, mobile phones, and social media have drastically reduced social isolation throughout the world.


4 At the same time, AI will create “physical moats” that make the world safer?

Will AI create moats of safety around countries, just like on the Ukraine/Russian front lines that have basically become a stable no-mans land? When AI tools quickly detect anything unsual, will aggression be impossible?


1 GPT ==================


1 The past → the future

50 years ago, nobody imagined PCs would change the world.
In the ARPANET days, home internet and search engines were unimaginable.

What changed everything was not just technology, but access.

AI is similar.
The real shift is not just better models, but:

  • easier tools
  • lower barriers
  • faster system creation

AI Dev Tools + agents → anyone can build working systems.


2 The real shift (not just better models)

The common view:

AI = smarter LLMs

The actual shift:

  • LLM = component
  • System = value

Future systems:

  • agent (core logic)
  • tools (APIs, workflows)
  • data (state)
  • LLM (replaceable)


3 Fast system creation

Near future:

  • describe system → system exists
  • minimal manual coding
  • rapid iteration

“Spinning up” systems becomes the core skill.

Not vibe coding.
Structured, efficient system building.


4 The physical world (Karp)

Key idea:

  • digital is easy
  • physical is hard

Jobs involving:

  • physical work
  • real-world troubleshooting
  • unpredictable environments

are harder to automate.

AI will:

  • assist these jobs
  • increase productivity
  • increase value of skilled workers

AI + physical world = moat


5 Removing barriers

AI reduces:

  • technical complexity
  • knowledge gaps
  • build time

Result:

  • more builders
  • more systems
  • more real-world impact


6 Open question

If systems can:

  • detect anomalies instantly
  • coordinate responses
  • operate continuously

Does this create:

  • safer systems?
  • stable environments?
  • new forms of control?

Unclear.


7 Summary

AI future = system building at scale

  • tools → faster builds
  • agents → orchestration
  • LLMs → components

The advantage shifts to those who can build complete systems quickly.


2 CLAUDE ==================


1 Nobody saw it coming

50 years ago — Commodore, Atari, ARPANET — nobody imagined PCs or the internet would reshape civilization. The search engine was unthinkable. What we take for granted today was science fiction.

AI will be bigger. And the end state is something we probably can’t yet imagine.


2 The immediate shift: AI tools for everyone

AI IDEs and tools are becoming reliable enough that non-developers can build sophisticated apps — perhaps just by chatting with an AI. The barrier between “idea” and “working software” is collapsing.

This is what this site is about: tracking that collapse in real time.


3 What about jobs? Karp’s “physical world” thesis

Palantir CEO Alex Karp argues AI will trigger a blue-collar renaissance, not mass unemployment. His reasoning:

  • Physical work is hard to automate. Electricians, plumbers, mechanics navigate messy real-world conditions AI can’t easily replicate.
  • AI as superpower, not replacement. Skilled tradespeople with AI tools outperform those without.
  • Re-industrialization drives wages up. Demand for hands-on labor increases as AI accelerates physical-world projects.

The white-collar knowledge worker may be more at risk than the electrician.


4 AI removes barriers — brings people together

Imagine discussing a complex app with an AI tool and having it built by morning. Or navigating bureaucracy, healthcare, legal systems — with an AI that knows your situation and speaks the language.

AI reduces man-made complexity. Just as mobile phones and the internet collapsed distance and isolation, AI may collapse the gap between what people need and what they can access.


5 AI moats — does aggression become impossible?

The Ukraine/Russia front lines have largely stabilized into a drone-and-sensor no-man’s-land. Neither side can move without being detected.

Will this scale globally? When AI systems can instantly detect any unusual movement — at borders, at sea, in the air — does large-scale aggression become self-defeating?

The drone with zipties may be an early glimpse of that future.


3 CURSOR ==================


1 The past, the future

Fifty years ago, few guessed PCs (Commodore, Atari…) would remake everything. ARPANET era: no one bet on home broadband + search sitting on the couch unfathomable, then mundane. AI’s impact will probably feel the same—we haven’t pictured the big shifts yet. Near-term guess: AI IDEs get dependable enough that non-specialists ship serious apps—maybe mostly by chatting with their IDE. This page is WIP: a sketch of where things might tilt, not a forecast.

2 Karp → “physical world” / blue-collar

Paraphrase of public commentary by Palantir CEO Alex Karp (not verbatim; check primary interviews if you cite formally).

  • Skilled trades up, not dead: electricians, plumbers, mechanics—hands-on troubleshooters gain leverage.
  • “Physical moat”: messy real-world conditions resist full automation versus routine desk work.
  • Augmentation: AI as power tools for trades, not wholesale replacement (that’s his angle).
  • Wages: re-industrialization + AI infra could lift demand for field labor (US-centric version of his story). His drift: futures favor vocational × AI, less “pure spreadsheet jobs.”

3 Apps from conversation; barriers dropping

Sketch: ship complex apps by iterate-and-talk with agents/IDE helpers. Strip away needless friction—the artificial complexity we layered on bureaucracy, boilerplate, integration hell. Bold hope: coordination gets easier.Counter-hope: the same stacks can amplify spam, scams, polarization—internet 2.0 trade-offs still apply.Net effect unknown.

4 Surveillance moats / “frozen” borders?

Thought experiment—not policy claim. Cheap sensors + fast models → unusual activity flags everywhere. Ukraine/Russia trench-line metaphor: grinding stalemate masking heavy violence—not “peace,” just inertia. Question I’m chewing on:**does widespread machine-speed detection blunt escalation—or just move it asymmetrically/offline?