Urgent.News

What's breaking now, across hundreds of outlets.

AI

We’ve Found the Only Good AI Chatbot: One So Tiny It Fits on a Single MS-DOS Floppy Disk

It's also incredibly dumb. The post We’ve Found the Only Good AI Chatbot: One So Tiny It Fits on a Single MS-DOS Floppy Disk appeared first on Futurism .

We’ve Found the Only Good AI Chatbot: One So Tiny It Fits on a Single MS-DOS Floppy Disk

In an age of gargantuan AI models, a diminutive chatbot stands out as the only good "LLM" in Hackaday's eyes. Measuring just 380 KB, it can fit on a single floppy disk and run on an MS-DOS computer from the 1980s. Despite its tiny size, the simple transformer model was trained on 3,500 facts and uses Anthropic Fable 5.2 and Opus 5.5 for creation and training.

Its interface bears a retro charm, providing correct answers like whales being mammals and Alexander Graham Bell inventing the telephone. However, it also makes up answers, such as 17 times 23 equaling 96 and that the king of France is named "Antarce Newton."

Rewritten by urgent.news; may contain errors — check the original.

Read the original at futurism.com →

Report a problem with this story

More in AI

Gemini 4 Neon Costs More Per Token and Less Per Task

Carbon costs $2 per million input tokens. Neon costs $3 per million input tokens. Same family, same 1M context window, and the cheaper one has the higher price tag.

  • Gemini 4 Neon launched on November 18, 2026, as a "frontier-level intelligence at lower cost"
  • Higher price per token compared to Carbon predecessor, causing user confusion
  • Neon excels in complex tasks like legal research and tax analysis, but falls short in Code Migration

Your AI Agent Wrote Code. Where Does It Run? A Sandbox Runner in Under 50 Lines of Python

Your AI agent just wrote some Python and wants to run it. Where does that code actually execute? For a lot of agent products the honest answer is "on the same server as everything else, with the same…

  • Sandbox runner implemented in under 50 lines of Python
  • Limits CPU usage, memory usage, file size, wall clock time, output size
  • Executes code in separate process group with restricted environment variables

Upscaling AI-Generated Video to 4K: Resolution, Bitrate, Frame Rate and Artifacts

Disclosure: I'm writing this as part of the VideoUpscalerAI team. The product-specific numbers below come from our own published docs, and the rest is general video engineering that applies to any…

  • 4K upscaling requires consideration of resolution, bitrate, frame rate and artifacts
  • Integer scale factors (2×) are cleaner than higher fixed factors
  • Generated footage often shows artifacts like smeared textures and blocky compression

Agentic AI for Payment Exceptions in LangGraph: Deadline Triage, Sanctions Hits & a Release the LLM Must Never Make

Payments is the domain where "the happy path is already automated" is most literally true — straight-through processing has existed for decades, and a clean payment never touches a human.

  • Agent classifies exception types and urgency using a small model
  • Escalates high-value exceptions with <30 minutes remaining deadline
  • Drafts discrimination narrative for sanctions hits but cannot clear false positives

More from Saturday 21 November →