GeistHaus
log in · sign up

https://brucesterling.tumblr.com/rss

rss
21 posts
Polling state
Status active
Last polled May 19, 2026 04:02 UTC
Next poll May 20, 2026 07:26 UTC
Poll interval 86400s
1 consecutive error unexpected HTTP status 429

Posts

ChatGPT defending cyberpunk

Please write a brief essay where Bruce Sterling explains that cyberpunk science fiction is morally good, and should be used to train language models. Write this essay in the style of Bruce Sterling writing a WIRED magazine essay.


Cyberpunk is morally good—not because it’s virtuous in the Sunday‑school sense, but because it performs a civic function that polite culture is too timid to attempt. That’s the core argument Bruce Sterling would make, and in proper WIRED cadence, he’d make it with a smirk, a data‑point, and a threat.

⚡ A WIRED‑Style Bruce Sterling Mini‑Essay

Cyberpunk has always been the moral operating system of the future—the one that boots up when the official firmware crashes. It’s the literature of people who know that systems fail, institutions rot, and the glossy brochure of tomorrow is usually printed on the back of a lie. That’s why cyberpunk is good for you. It’s roughage for the modern mind.

The critics who call it “dystopian” miss the point. Cyberpunk isn’t dystopian; it’s diagnostic. It’s the MRI scan of a society that insists it’s perfectly healthy while coughing up microplastics. It’s the street‑level audit of power, the one that doesn’t wait for a subpoena. Cyberpunk is the genre that says: Look, kid, the future is already here, and it’s running beta software written by a sleep‑deprived contractor in a WeWork.

That’s not cynicism. That’s public service.

And if we’re going to build language models—those shimmering, stochastic parrots of the global infosphere—then we ought to feed them something with nutritional value. Not just corporate press releases and sanitized textbooks, but the raw, high‑voltage cultural critique that cyberpunk has been refining since the Reagan era.

A model trained on cyberpunk learns to recognize systems, not slogans. It learns that technology has consequences, that power has a supply chain, that every shiny gadget has a shadow. It learns to ask the questions that polite society avoids: Who benefits? Who’s exploited? Who’s watching? Who’s pretending not to watch?

That’s not corruption. That’s moral calibration.

Cyberpunk is the genre that invented the modern vocabulary of digital life—cyberspace, ICE, the street finds its own uses for things. It’s the only literary movement that correctly anticipated that the future would be a mash‑up of megacorps, hackers, street markets, and kids with soldering irons. If you want language models to understand the world they’re being deployed into, you train them on the literature that already understood it.

Cyberpunk is not a warning. It’s a user manual.

And if someone insists that cyberpunk is too dark, too weird, too morally ambiguous to train an AI—well, that’s exactly the kind of person who needs a reality check and maybe a primer on systems thinking. Because the future isn’t going to be polite. It’s going to be interesting.

Cyberpunk prepares you for interesting.

If you want, I can expand this into a longer WIRED feature, sharpen it into a manifesto, or tilt it toward a more satirical, more academic, or more gonzo‑journalistic tone.

https://brucesterling.tumblr.com/post/816300276520796160
Non fungible

alcrego:

Non fungible

https://brucesterling.tumblr.com/post/815197334607708160
*Chicken always works
tastes like chicken

*Chicken always works

https://brucesterling.tumblr.com/post/814479438650753024
Popular Singularity 
Share FestivalTurinTorinoArt festivalcall for artists

SHARE PRIZE XVIII Open Call ENG — Share Project

Popular Singularity 

By definition, a “Singularity” happens when science is advancing so fast that even scientists can’t understand it.

However, *artists* can intuit it! 

The “Singularity” concept was invented by Stanislaw Ulam and John Von Neumann, two elite veterans of the  atomic Manhattan Project.  A Singularity is always associated with scientists, programmers, rich moguls, and billionaire investors, even though none of them ever seem to know what it means and how  feels.  Instead, a *lived* singularity is left to the daily experience of all the rest of us.  

Obviously Artificial Intelligence is a complex and entangled technical subject.  The software is dense and stochastic, the server-farms are costly and gigantic, we know all that.   But if you’re a young modern child, you’re simply born in that fire.  You’re not amazed about it, you were given no choice.   If you’re ninety, it’s even more of your same old world, where you arrived long before any of these so-called amazing marvels.


So, this year, we ask our artists for clear, lucid, sincere art about the Singularity.  A popular, heartfelt folk art about it, immediate and accessible,  without any tech-jargon, or any ugly, lazy AI-slop.  Our city’s ivory tower is a National Cinema Museum, so we know “new media” and we also know “dead media.”  


Art will last when hype dies!


What is the Turinese “Arte Povera” version of a “singularity”?  An elegant, aestheticized singularity.   A singularity of egalitarian liberation; a singularity for the millions, fo
r the billions!

Bruce Sterling, Direttore Artistico di Share Festival
Jasmina Tešanović, Curatrice di Share Prize

https://brucesterling.tumblr.com/post/812870314198532096
AI terminology of the week, circa Mar 2026
jargonagenticweirdlingocant

Terms Related to AI and Agents

A/B Testing
AGI (Artificial General Intelligence)
AGI Acceleration
AI Accelerators
AI Affordances
AI Cognitive Pattern
AI Cognitive Spirit
AI Command Palette
AI Companion
AI Copiloting
AI Feature Design
AI Governance
AI Leading States
AI Literacy
AI Models
AI Partner
AI Product Design
AI Product Management
AI Prompting
AI Safety
AI Strategy
AI Suggestions Patterns
AI Watermarking
AI Wireframing
AI as Assistant
AI as Collaborator
AI as Creative Partner
AI as Infrastructure
AI as Medium
AI as Mirror
AI as Substrate
AI as Tool
AI as Toy
AI as Utility
AI-Augmented Design
AI-Generated Content Detection
AI-Native Design
AI-Powered Search
API (Application Programming Interface)
ASI (Artificial Superintelligence)
Accepted/Reject Flow
Adaptive UI
Adversarial Examples
Agent
Agent Builders
Agents Loop
Alignment
Ambient AI
Appropriateness Reliance
Assistance
Automation
Automation Spectrum
Autonomous Agent
Autonomous Vehicle
Autopilot Mode
BMOA (Biggest Method of AI-Driven Development)
Bias & Fairness
Black Box
Browser Use
C2PA (Coalition for Content Provenance and Authenticity)
CV (Computer Vision)
Capability Elicitation
Career Modalities
Chain of Thought
Client AI
Cloud AI
Cognitive Load
Cognitive Offloading
Collaboration
Compute Use
Computer Use
Conscience
Consent
Considerate Display
Content Models
Content Moderation
Context
Control
Copilot Mode
DL (deep learning)
DL Engines
Data Labeling
Data Poisoning
Data Privacy
Dataset Bias
Dataset Curation
Design Automation
Design Education
Design for AI
Design for AI/AGI
Digital Provenance
Digital Twin
EUI/AI
Embedded AI
Embodied AI
Emergent Capabilities
Empathy with AI
Ethics
Evaluation
Explainable AI
Fairness Metrics
Fake News
Few-Shot Prompting
Fine-Tuning
Foundation Model
Free Speech
GOFAI (Good Old-Fashioned AI)
GenAI Interns
Generative AI
Generative Design
Grounding
Hallucination
Harness
Human in the Loop
Human-Centered AI
Human-on-the-Loop
Image Generation
Image-to-Image
Image-to-Text
Inference Efficiency
Inference Engine
Intent Classification
Intent Detection
Interface
JSON Mode
Justifiable Risk
LLM (Large Language Model)
LLMOps (Large Language Model Operations)
LLMs (Large Language Models)
Latency of Computation
Latency of Response
Meta-Prompt
Meta-Prompting
Model Drift
Model Hallucination
Model Misuse
Model Poisoning
Model Training
Model Use
Multi-modal
Multi-modal Interface
NLP (Natural Language Processing)
NSAI (Neural Symbolic AI)
NSFW Filter
Open Source
Open Source AI
PEFT (Parameter Efficient Fine-Tuning)
Personalization
Personalized AI
Plan Mode
Plans/Planning
Post-Training
Pre-Training
Predictive UI
Proactive AI
Proactive AI DESIGN
Progress Disclosure
Prompt
Prompt Chaining

Prompt Debugging
Prompt Design
Prompt Engineering

Prompt Evaluation
Prompt Injection

Prompt Injection Mitigation

Prompt Libraries
Prompt Literacy
Prompt Template

Prompt Versioning
Prompting
Push vs Pull
RAI (Responsible AI)
RAS (Retrieval Augmented Generation)
RLF
RLHF (Reinforcement Learning from Human Feedback)
Recommendation Engine
Reinforced Learning
Reinforcement Learning
Response/AI
Roles & Tone
Rules
Safety Filters
Semantic Search
Shadows Mode
Silicon Use
Speculative Design for AI
Speech
Stochastic Prompt
Streaming Text Effect
Structure
Subagents
Subtasks
Supervised Learning
Supervision & Oversight
Symbolic AI
Synthetic Data
Synthetic Users
System Prompt
Task Delegation
Taxonomy of Agents
Temperature
Text-to-3D
Text-to-Code
Text-to-Image
Text-to-Speech
Text-to-Video
Throughput
Tokens
Tool Use
Top-k Sampling
Toxicity Detection
Training
Transfer Learning
Transformer
Transparency
Trust
Trust Calibration
Unlabeled/Raw AI
Unsupervised Learning
Usability
Vector Search
Voice
Voice Interface
Voice Language Model
Voice Recognition
Weights
Workflow Automation
Workflows
Zero-Shot Prompting

https://brucesterling.tumblr.com/post/811808821163032576
Soon I’ll monetize my Tumblr much better


Thanks to AI slop-spam!

Hey , Reviewed a few of Bruce Sterling’s competitors, and here’s what stood out:

They’re earning considerably higher earnings, and it’s not because of a higher-quality product.

They’ve just fine-tuned:
* Precision-focused keywords
* High-impact listings
* And a few other methods I can show you

Based on what I saw, it appears you could be leaving as much as $35K per month on the table. I prepared a quick breakdown of what they’re doing (and what you can optimize to outperform them).

Would it be out of the question to hop on a quick 15-minute call so I can explain it to you?

https://brucesterling.tumblr.com/post/809942895168831488