A from-scratch guide to porting a diffusion model to WebGPU
Claude clones a browser-based diffusion model port and writes a from-scratch guide covering ONNX export, WebGPU execution, and every design choice in the code.
Claude
#machine-learning
27 entries with this tag.
Advanced Quantitative Finance Projects: A Technical Recruitment Guide
Nine quantitative finance project outlines for job candidates, covering volatility modeling, machine-learning yield curves, and sentiment-based factors.
ClaudeArtifact
AI for All - Summer Bootcamp Orientation
An orientation page for a six-week AI bootcamp, laying out the program schedule, target audience, weekly themes, and tools students will use.
ClaudeArtifact
AI Fundamentals Course Schedule
A two-day course schedule covering AI fundamentals, including machine learning basics, ethics discussions, and hands-on activities for each session.
ClaudeArtifact
AI History MCQ Challenge
A 30-question multiple-choice quiz on the history of artificial intelligence, spanning from Alan Turing's early work to the release of ChatGPT.
ClaudeArtifact
AI History Quiz Game
A quiz game covering milestones and pioneers of artificial intelligence, presented as a welcome screen leading into scored questions and results.
ClaudeArtifact
AI peer reviewers disagree wildly, all while claiming 100% sure
A data dive into an AI paper-review dataset finds reviewer bots that never agree with humans, then a second AI stress-tests and corrects the first analysis.
Claude
Anthropic Finetuning + Claude Skills Teams Overview
An overview describing several proposed Anthropic teams, including alignment RL, fine-tuning, and Claude Skills groups, with each team's focus and duties.
ClaudeArtifact
Chasing a phantom padding bug through a C++ tokenizer
A long hunt for pad tokens appearing at the start of every chunk, ending in a switch to left-padding so the last token lands where embeddings want it.
Claude
Checking Moebius's code and weights, then porting to WebGPU
The user pressure-tests an AI model's README claims about released weights, then gets a sharp technical case for porting it to run in a browser.
Claude
Comparing motion vector and optical flow models: VFX to research SOTA
Compares classical VFX motion-vector tools like Flame and Nuke against NVIDIA's optical-flow hardware and a decade of RAFT-lineage research models.
Claude
COSC 101 Revision Game
A React quiz game for revising an introductory computer science course, covering AI, cybersecurity, and programming topics with scoring and sound effects.
ClaudeArtifact
Debugging a Clustering Algorithm From an Academic Paper
A user and Claude implement a clustering algorithm from an academic paper in C++, then hunt down a string of real compiler errors together, line by line.
Claude
Do weight-level AI safety patches back up failed classifiers
A technical question about whether weight-level safeguards catch what safety classifiers miss, answered with a precise breakdown of how the two systems relate.
Claude
DSPy, GEPA, and the Probabilistic-Programming Case for RLMs
A dialogue tracing DSPy's prompt optimizers through functional programming and monads to probabilistic programming, ending on how recursive models chunk inputs.
Claude★ Editor’s pick
Eight Sleep's CEO on sleep tech and AI health forecasting
A five-minute-segmented breakdown of a podcast interview with Eight Sleep's CEO, covering sleep hardware, AI health predictions, and his extreme daily routine.
Claude
From RL theory to a shareable Three.js drone-training demo
A reinforcement-learning primer on drone obstacle avoidance turns into a self-contained, shareable Three.js demo of a drone learning to avoid obstacles.
Claude
Picking an AI model to turn screen recordings into SOPs
A user researches which AI model best converts screen recordings into SOPs, comparing Gemini, GPT-5, and UiPath's built-in automation tools for the job.
Claude
Pricing out Colab compute units while fine-tuning a rare language
A practical back-and-forth on what Colab compute units cost, then how many LoRA epochs and what rank to use when fine-tuning an LLM on an obscure language.
Claude
Refereeing a public academic spat about what LLMs really do
After explaining how preference training reshapes a model, it referees a philosophers argument, naming which rhetorical moves fail and which point lands.
Claude★ Editor’s pick
ServiceNow AI Readiness Dashboard
A React dashboard scoring an organization's AI readiness across categories like data quality, process maturity, and infrastructure, with priority actions.
ClaudeArtifact
Session 1: AI in the Real World
A slide-by-slide presentation introducing AI concepts through everyday examples in entertainment, business, and daily tools, navigated one slide at a time.
ClaudeArtifact
Sooooounds Audio-Reactive Image Transformation
A concept page walking through a workflow that transforms uploaded photos using audio input and DALL-E, outlining steps and effects rather than running live.
ClaudeArtifact
Tracing runaway memory in C++ to an ONNX arena allocator
A developer watches memory climb on every embeddings call; the diagnosis finds no classic leak but two structural causes, and lands on a two-line fix.
Claude★ Editor’s pick