Research you can check yourself.
Good science is something you can question. We show you where each example comes from, who reviewed its publication, and which claims about this site's implementation have not been independently checked.
Peer review is not a magic stamp.
A journal or conference paper may be peer reviewed. A government standard can undergo public comment instead. An author's technical report may have neither type of formal review. These are different publication processes, not a simple ranking of truth.
Research does not certify our code.
None of the interactive experiments on this site has a documented independent third-party audit. Automated tests can catch mistakes, but passing them is not equivalent to independent verification, replication or external certification.
Neural network forward pass
Research & verificationNeural network forward pass
Publication review: Peer-reviewed scientific journal article.
Independent verification: Our 2 → 3 → 1 network uses custom illustrative parameters. Its numerical calculations have automated tests, but no independent party has audited its educational or mathematical correctness.
Peer review of a paper does not certify this demo.
Subword tokenization
Research & verificationSubword tokenization
Publication review: Peer-reviewed conference paper published in ACL proceedings.
Independent verification: The homepage visualizer is a toy word/punctuation splitter, not the paper's BPE algorithm. It has unit tests but no third-party audit.
Peer review of a paper does not certify this demo.
Learned vector representations
Research & verificationLearned vector representations
Publication review: Peer-reviewed conference publication; relevant to vector representations, not an audit of these particular GPT-2 weights.
Independent verification: We read actual FP32 token-embedding rows from the publicly hosted DistilGPT-2 checkpoint using byte ranges. No third party has validated this site's extraction procedure.
Original weight file (public metadata) ↗Peer review of a paper does not certify this demo.
Learning through gradient descent
Research & verificationLearning through gradient descent
Publication review: Peer-reviewed scientific journal article.
Independent verification: Our training experiment is original scalar regression, not an experimental reproduction of the paper. Its math has unit tests, not external certification.
Peer review of a paper does not certify this demo.
Scaled dot-product attention
Research & verificationScaled dot-product attention
Publication review: Peer-reviewed machine-learning conference paper.
Independent verification: Our query/key numbers are invented teaching values. The attention implementation has unit tests but has not been independently reviewed.
Peer review of a paper does not certify this demo.
Generative language modeling
Research & verificationGenerative language modeling
Publication review: Public technical report; not a peer-reviewed conference or journal publication.
Independent verification: The inference panel uses the public DistilGPT-2 checkpoint and Transformers.js. Its browser integration is not independently audited or benchmark-certified.
Public DistilGPT-2 model card ↗Peer review of a paper does not certify this demo.
Transformers and next-token prediction
Research & verificationTransformers and next-token prediction
Publication review: Peer-reviewed conference publication that established the Transformer architecture. GPT-2 autoregressive decoding is a later development.
Independent verification: The step-by-step explanations summarize a typical autoregressive pipeline; they are not independently audited claims about any single deployed model.
Peer review of a paper does not certify this demo.
Responsible use of AI systems
Research & verificationResponsible use of AI systems
Publication review: Publicly reviewed, consensus-developed U.S. government framework; not conventional academic journal peer review.
Independent verification: The site summarizes risk categories but has not had independent expert evaluation for completeness.
Peer review of a paper does not certify this demo.
Evaluating AI-generated code
Research & verificationEvaluating AI-generated code
Publication review: Peer-reviewed security research paper. Its historical results concern the model and methodology tested, not every modern coding assistant.
Independent verification: The site's engineering examples are illustrative and are not an independent security audit or certification.
NIST Secure Software Development Framework ↗Peer review of a paper does not certify this demo.