Token
A blockchain-based digital asset; a network token is a claim on a company's future digital network value, distinct from debt or equity.
As defined in cwt_balaji-srinivasan
Other definitions
The unit of text a language model predicts—can be a letter, word, or punctuation mark—forming a larger set than just an alphabet.
The Strange Math That Predicts (Almost) Anything
Where it comes up · 53
- Designing LLM Systems PART 1 Foundations Chapter 1 AI Systems Architecture The Real Currency of AI17 claims
- Hash Power – Part 113 claims
- 90 - 5 Mental Models for Web3 | Chris Dixon11 claims
- This Tiny Engine Runs Impossibly Big AI Models Locally! (colibrì)10 claims
- A Quick Lesson Of AI Languages10 claims
- Metas AI Boss Says He DONE With LLMS...7 claims
- AI Trends 2025: Mary Meeker Deck Deep Dive Part 16 claims
- Breakthrough potential of AI | Sam Altman | MIT 20235 claims
and 45 more
Most important claims · 10 of 174Search all claims for “Token” →
- There is an intuitive assumption that if data is in the context window, the model will use it, but research suggests otherwise: as context windows grow to 500,000 tokens, the model's attention mechanism becomes diluted, and the model often fails to retrieve or hallucinates details from text that is buried in the middle of very large documents.Is RAG Still Needed? Choosing the Best Approach for LLMs
- AI systems do not process language the way humans do—they break sentences into discrete tokens rather than reading sentences fluidly, fundamentally changing how they parse meaning.Designing LLM Systems PART 1 Foundations Chapter 1 AI Systems Architecture The Real Currency of AI
- The core function of a large language model is to predict the probability of the next token given a sequence of prior tokens, and it performs this prediction iteratively (one token at a time) to generate complete sentences, paragraphs, and answers.Designing LLM Systems PART 1 Foundations Chapter 1 AI Systems Architecture The Real Currency of AI
- Modern large language models operate on tokens (letters, words, or punctuation) rather than just an alphabet, predicting the odds of the next token given a string of prior tokens—but unlike simple Markov chains they use 'attention' to decide which prior tokens matter, allowing context like 'blood' and 'mitochondria' to disambiguate that 'cell' means biology rather than a prison.The Strange Math That Predicts (Almost) Anything
- A decentralized autonomous organization pools crowdfunded cryptocurrency in a smart contract, issues tokens, and has no individual with access; token holders vote to allocate funds, making them shareholders in a protocol rather than a company, with no legal entity behind it.Hash Power – Part 3
- Tokens are not always full words—words can be broken into multiple tokens (e.g., 'unbelievable' becomes 'un', 'believe', 'able'), allowing the model to understand linguistic building blocks like prefixes, suffixes, and roots.Designing LLM Systems PART 1 Foundations Chapter 1 AI Systems Architecture The Real Currency of AI
- Generative video prediction models that directly predict pixel values produce blurry outputs because they cannot enumerate the ~10^15 million possible next frames the way language models enumerate discrete tokens, forcing them to average pixel values across uncertain outcomes.Yann LeCun's $1B Bet Against LLMs [Part 1]
- Tokens are discrete representations from a finite set (typically ~100,000 tokens in LLMs), but the physical world is continuous and high-dimensional, making token-based prediction unsuitable for modeling natural continuous phenomena.Metas AI Boss Says He DONE With LLMS...
- Within a context window, every single token counts toward a total token budget for a single interaction, including the user's question, system instructions, background information retrieval, and the generated answer—all competing for the same limited allocation.Designing LLM Systems PART 1 Foundations Chapter 1 AI Systems Architecture The Real Currency of AI
- Text is tokenized into discrete units, each token is assigned a numeric ID from a dictionary, and that ID is converted into a complex vector (embedding) that represents the token's meaning in mathematical form.Designing LLM Systems PART 1 Foundations Chapter 1 AI Systems Architecture The Real Currency of AI