This interactive application provides a dynamic turtle graphics environment inspired by the TT2500 machine. It enables users to create complex geometric animations through commands for vector movement and specialized "moving plates." These plates can perform various actions such as spinning, sliding, scaling, oscillating, or shifting colors. Because these plates support nesting, they allow for the creation of sophisticated epicyclic motion patterns within a single program.
Core capabilities include:
- Vector navigation via forward, backward, and rotation commands
- Dynamic plate mechanics including spin, move, grow, wag, bob, pulse, and hue shift
- Color manipulation using HSL values for smooth transitions
- Nested animation structures to create layered geometric movement
- Recording tools for real-time webm video or high-fidelity frame sequences
Core capabilities include:
- Vector navigation via forward, backward, and rotation commands
- Dynamic plate mechanics including spin, move, grow, wag, bob, pulse, and hue shift
- Color manipulation using HSL values for smooth transitions
- Nested animation structures to create layered geometric movement
- Recording tools for real-time webm video or high-fidelity frame sequences
Reviving a 47-year old variant of the Logo programming language with Claude’s help
Ken Kahn used the Gemini Antigravity 2.0 app, powered by Gemini 3.5 Flash, to resurrect approximately 500 files and projects from his time at the MIT AI Lab in the late 1970s.
The app successfully reincarnated three old projects: the Director programming language, the Ani program (based on his doctoral thesis), and the Diagrammer system.
The main glitch was Gemini's persistent misinterpretation of Kahn's TT2500 real-time animation programs as dynaturtle programs. Kahn resolved this by prompting Claude Opus 4.7 for a clear explanation of the TT2500's dynamic, nested coordinate frames (a plate mounted on a plate), then generating and integrating the correct code into Antigravity.
The app successfully reincarnated three old projects: the Director programming language, the Ani program (based on his doctoral thesis), and the Diagrammer system.
The main glitch was Gemini's persistent misinterpretation of Kahn's TT2500 real-time animation programs as dynaturtle programs. Kahn resolved this by prompting Claude Opus 4.7 for a clear explanation of the TT2500's dynamic, nested coordinate frames (a plate mounted on a plate), then generating and integrating the correct code into Antigravity.
This article details an iterative process of using ChatGPT to explore the parallels between Marvin Minsky's "Society of Mind" and Anthropic's research on Large Language Models, specifically Claude Haiku. The user experimented with different prompts to refine the AI's output, navigating issues like model confusion (GPT-2 vs. Claude) and overly conversational tone. Ultimately, prompting the AI with direct source materials (Minsky’s books and Anthropic's paper) yielded the most insightful analysis, highlighting potential connections like the concept of "A and B brains" within both frameworks.
>"The author of The Learner's Apprentice: AI and the Amplification of Human Creativity, Ken Kahn sits down with CMK Press President Sylvia Martinez to discuss his new book, learning, and artificial intelligence. In this video, Dr. Kahn shares some of the sorts of hundreds of projects explored in his best-selling new book."
Learn more about the new book: https://amzn.to/41cQgY0
Learn more about the new book: https://amzn.to/41cQgY0
The paper "The Pursuit of Pseudocode Programming: Can LLMs Bridge the Gap?" explores the potential of Large Language Models (LLMs) to make pseudocode executable, addressing long-standing challenges in pseudocode programming. Pseudocode, known for its human-readable style, has been valuable for planning, communication, and education but has faced issues like lack of standardization, ambiguity, and limited expressiveness. LLMs offer new possibilities by handling ambiguity, generating code from pseudocode, and enhancing its expressiveness. Recent developments like SudoLang and pseudocode injection techniques demonstrate the potential of LLMs in this area. However, challenges remain in ensuring accuracy, reliability, and ethical considerations of LLM-generated code.
Key points:
- Pseudocode's benefits include improved efficiency, readability, and collaboration.
- Challenges include lack of standardization, ambiguity, and limited expressiveness.
- LLMs can interpret informal pseudocode, generate code, and enhance expressiveness.
- Developments like SudoLang and pseudocode injection show promise.
- Challenges include accuracy, debugging, and ethical considerations.
Key points:
- Pseudocode's benefits include improved efficiency, readability, and collaboration.
- Challenges include lack of standardization, ambiguity, and limited expressiveness.
- LLMs can interpret informal pseudocode, generate code, and enhance expressiveness.
- Developments like SudoLang and pseudocode injection show promise.
- Challenges include accuracy, debugging, and ethical considerations.
Ken Kahn created a Chrome extension with the help of ChatGPT 4o that provides the contextual meaning of words selected on web pages. The extension prompts an LLM to provide a brief definition of the selected word within its context. The project involved generating files for a Chrome extension, replacing alerts with custom popups, and enhancing the sentence-finding feature.
- Embeddings transform words and sentences into sequences of numbers for computers to understand language.
- This technology powers tools like Siri, Alexa, Google Translate, and generative AI systems like ChatGPT, Bard, and DALL-E.
- In the early days, embeddings were crafted by hand, which was time-consuming and couldn't adapt to language nuances easily.
- The 3D hand-crafted embedding app provides an interactive experience to understand this concept.
- The star visualization method offers an intuitive way to understand word embeddings.
- Machine learning models like Word2Vec and GloVe revolutionized the generation of word embeddings from large text datasets.
- Universal Sentence Encoder (USE) extends the concept of word embeddings to entire sentences.
- TensorFlow Projector is an advanced tool to interactively explore high-dimensional data like word and sentence embeddings.
- This technology powers tools like Siri, Alexa, Google Translate, and generative AI systems like ChatGPT, Bard, and DALL-E.
- In the early days, embeddings were crafted by hand, which was time-consuming and couldn't adapt to language nuances easily.
- The 3D hand-crafted embedding app provides an interactive experience to understand this concept.
- The star visualization method offers an intuitive way to understand word embeddings.
- Machine learning models like Word2Vec and GloVe revolutionized the generation of word embeddings from large text datasets.
- Universal Sentence Encoder (USE) extends the concept of word embeddings to entire sentences.
- TensorFlow Projector is an advanced tool to interactively explore high-dimensional data like word and sentence embeddings.
