惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Microsoft Azure Blog
Microsoft Azure Blog
GbyAI
GbyAI
P
Proofpoint News Feed
Engineering at Meta
Engineering at Meta
Recent Announcements
Recent Announcements
L
LangChain Blog
B
Blog
阮一峰的网络日志
阮一峰的网络日志
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
M
MIT News - Artificial intelligence
D
Docker
WordPress大学
WordPress大学
J
Java Code Geeks
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
The GitHub Blog
The GitHub Blog
博客园 - 叶小钗
Last Week in AI
Last Week in AI
Stack Overflow Blog
Stack Overflow Blog
有赞技术团队
有赞技术团队
MyScale Blog
MyScale Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
MongoDB | Blog
MongoDB | Blog
博客园 - Franky

Hacker News: Front Page

SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Introducing Claude Opus 4.7 Qwen Studio The Future of Everything is Lies, I Guess: Where Do We Go From Here? GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis Ancient DNA reveals pervasive directional selection across West Eurasia [pdf] AI cybersecurity is not proof of work Moving a large-scale metrics pipeline from StatsD to OpenTelemetry / Prometheus GitHub - Nightmare-Eclipse/RedSun: The Red Sun vulnerability repository GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. A Better Ludum Dare; Or, How to Ruin a Legacy GitHub - macOS26/Agent: Any AI, replaces Claude Code, Cursor, OpenClaw. Over 18 LLM providers (Claude, OpenAI, Gemini, Ollama, Zai, HF, Qwen) wired into a native Mac app that writes code, builds Xcode projects, bumps versions, manages git, automates Safari, use AppleScript, JS or Accessibility, extend Agent! w/ MCP Servers, run tasks from your iPhone via Messages. YouTube now lets you turn off Shorts I Made a Terminal Pager Burgers | マクドナルド公式 Commands — HackerNews CLI documentation ChatGPT for Excel PiCore - Raspberry Pi Port of Tiny Core Linux Live Nation illegally monopolized ticketing market, jury finds Google Broke Its Promise to Me. Now ICE Has My Data. Founding Engineer at Adaptional | Y Combinator CRISPR takes important step toward silencing Down syndrome’s extra chromosome GitHub - saffron-health/libretto: The AI toolkit for building reliable browser automations US v. Heppner (S.D.N.Y. 2026) no attorney-client privilege for AI chats [pdf] Unexpected €54k billing spike in 13 hours: Firebase browser key without API restrictions used for Gemini requests Fragments: April 14 Cal.com Goes Closed Source: Why AI Security Is Forcing Our Decision | Cal.com - Scheduling Software for Online Bookings Laravel raised money and now injects ads directly into your agent Codex Hacked a Samsung TV
That time I asked AI to write Sci-Fi for eternity • F055
f055 · 2026-05-13 · via Hacker News: Front Page

Last year I discovered I like sci-fi novels. To be precise, I found a collection of Isaac Asimov sci-fi novels and started reading them in the evenings to unwind. I know Asimov wrote the Foundation saga and more, but my particular interest in his novels was very specific: I wanted to find something to read, and finish, in one or two evenings. Over the years, I grew a slight disgust for ultra-long forms that drag on like soap operas, no matter how epic or interesting.

However, I finished the collection of Asimov’s novels rather quickly, and with enjoyment. I wanted to read more such novels, but sadly I couldn’t find further collections by Asimov. And even if there was another collection, I think a human person has a finite amount of time in life and can’t write an infinite amount of novels. But AI can. Hence my new side project.

My first approach, ironically, resulted in what I have a disgust for: a Never-Ending Novel written one paragraph per day by two frontier models. While the AI created some interesting sci-fi concepts and made the story mostly appealing, each day it was inevitably going into the direction of a never-ending space opera. And, of course, included some annoying AI slop constructs like hyperbolic negation, plenty of “not buts”, or the main character’s urge to always reply in contradictions, like some different kind of Yoda: whenever anyone said anything, Olda would reply with “It was not that but this.”

That said, AI also came up with some amazing lines like:

“Civilization begins wherever mercy becomes auditable.”

“On Mars, coincidence had long ago been the name of things understood too late.”

“Home is not the place one left but the practice one carried outward and found, on return, still running.”

From technical point of view the backend is just a straightforward Perl script that calls AI APIs and rotates between the two AI models based on which was the one to write the last paragraph, and all data is stored directly in the HTML file that is used to display the novel on the Never-Ending Novel URL. On the frontend, there’s even a quite slick auto-bookmark tracking the reader’s progress as they scroll down the page. As time of writing NEN has 75 paragraphs and the story could be wrapped up.

My second approach resulted in something else: Novel Index where the same two frontier AIs write a novel up to a random amount of paragraphs within a fixed range (like 75 to 100), and then move on to start another story. This approach looks more like what I was looking for. The AIs create a collection of novels, short enough to read in one or two evenings, using the same backend and frontend features as NEN, and still heavily inspired by Isaac Asimov’s work.

But this time, the novels are not never-ending! Instead, they just keep stacking on a virtual shelf, novel after novel. If you need something to unwind, but you’ve read all your favourite authors, maybe this is something for you: Novel Index. Just ignore the occasional AI slop. The overall story arch should be worth it anyway, if you are lucky: AI writing is just like a box of chocolates…

I'm a '08 graduate of Oxford University Computing Laboratory with M.Sc. in Computer Science having studied Machine Learning, Intelligent Systems, Information Extraction and Semantic Annotation. Since then, I have created & been involved in many projects, using various technologies.

I like to code in Perl, Solidity & jQuery+JavaScript, deploy on Ethereum & Debian+Nginx, design with Adobe & Affinity, and learn new things all the time!