Login
Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
(github.com) by Bibabomas | view | 150 comments
Home Depot GitHub token exposed for a year, granted access to internal systems
(techcrunch.com) by kernelrocks | view | 161 comments
State of AI: An Empirical 100T Token Study with OpenRouter
(openrouter.ai) by anjneymidha | view | 95 comments
Cerebras Code now supports GLM 4.6 at 1000 tokens/sec
(cerebras.ai) by nathabonfim59 | view | 129 comments
From text to token: How tokenization pipelines work
(paradedb.com) by philippemnoel | view | 20 comments
BlackRock's Larry Fink: "Tokenization", Digital IDs, & Social Credit
(thewinepress.substack.com) by sbuttgereit | view | 83 comments
GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras
(cerebras.ai) by samspenc | view | 29 comments
Crypto hoarders dump tokens as shares tumble
(arstechnica.com) by Bender | view | 62 comments
Show HN: Tokenflood – simulate arbitrary loads on instruction-tuned LLMs
(github.com) by twerkmeister | view | 0 comments
Show HN: I'm a pastor/dev and built a 200M token generative Bible
(anselm-project.com) by mrprmiller | view | 12 comments
Show HN: CTON: JSON-compatible, token-efficient text format for LLM prompts
(github.com) by daviducolo | view | 1 comments
Show HN: Token Economics Calculator for AI inference hardware
(tensordyne.ai) by paul_td | view | 0 comments
An Abstract Arsenal: Future Tokens in Claude Skills
(jordanmrubin.substack.com) by RhysU | view | 0 comments
Crims Poison 150K+ NPM Packages with Token-Farming Malware
(theregister.com) by jruohonen | view | 1 comments
JPMorgan Steps Further into Crypto with Tokenized Money Fund
(wsj.com) by bookofjoe | view | 1 comments
SSE sucks for transporting LLM tokens
(zknill.io) by zknill | view | 1 comments
The 1B Token Challenge: Finding the Perfect Pre-Training Mix
(huggingface.co) by codelion | view | 0 comments
Show HN: CodeBurn – Analyze Claude Code token usage by task
(github.com) by agentseal | view | 0 comments
Why Early Tokens Matter, and How Tree-of-Thoughts Tries to Fix It
(bindlegal.com) by tatumakseliii | view | 0 comments
Reducing MCP token usage by 100x – you don't need code mode
(speakeasy.com) by crumbaugh | view | 0 comments
Token embeddings violate the manifold hypothesis
(arxiv.org) by airstrike | view | 0 comments
Singapore to trial tokenised bills, bring in stablecoin laws -central bank chief
(reuters.com) by thunderbong | view | 0 comments
Show HN: Skim – 90% token reduction for LLM code analysis
(github.com) by dean0x | view | 5 comments
Popular LiteLLM PyPI package backdoored to steal credentials, auth tokens
(bleepingcomputer.com) by billybuckwheat | view | 0 comments
Calm: LLMs That Predict Vectors Instead of Tokens
(shaochenze.github.io) by IndignantTyrant | view | 0 comments
Former NYC Mayor Eric Adams Accused of Crypto Pump and Dump with NYC Token
(gizmodo.com) by pseudolus | view | 0 comments
Picking Optimal Token IDs
(notes.hella.cheap) by todsacerdoti | view | 0 comments
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and Voice Cloning
(github.com) by chaosprint | view | 0 comments
LatentMAS – agent collaboration from token space into the model's latent space
(arxiv.org) by vismit2000 | view | 1 comments
SSE sucks for transporting LLM tokens
(zknill.io) by zknill | view | 0 comments
Agentic outcome/token based pricing
by mckinnonr | view | 0 comments
Token-Oriented Object Notation (TOON)
(github.com) by surprisetalk | view | 1 comments
Token Embeddings Violate the Manifold Hypothesis
(arxiv.org) by lukeplato | view | 1 comments
It Is All about Token: Towards Semantic Information Theory for LLMs
(arxiv.org) by dboreham | view | 0 comments
Token-Oriented Object Notation (Toon)
(github.com) by kyahwill | view | 0 comments
Breaking the Million-Token Barrier
(techcommunity.microsoft.com) by henrikhorluck | view | 0 comments
The 1B Token Challenge: Finding the Perfect Pre-Training Mix
(huggingface.co) by codelion | view | 0 comments
Readweb: Extract token-efficient Markdown from websites
(github.com) by klntsky | view | 0 comments
DeepSeek is 17% of token volume, Anthropic is 65% of spend (Vercel gateway data)
(vercel.com) by mcchen51 | view | 0 comments
Linux Foundation launches Tokenomics Foundation for AI token cost management
(tokeneconomics.com) by berlianta | view | 0 comments
One Token at a Time
(unvoid.substack.com) by nullscribe | view | 0 comments
"token" changed its default meaning from crypto to AI
(dd688.substack.com) by duanduankate | view | 0 comments
"80% of the economic value of LLMs come from 20% of the tokens"
(xcancel.com) by somic | view | 0 comments
CIYA – 91.53% token reduction, private hardware, no wrappers
(iiio.co) by iiiiiiiiio | view | 1 comments
The End of Free Tokens
(douwe.com) by dosinga | view | 0 comments
Chinese Sell "Claude" Tokens at 5% Cost While Making Millions
(twitter.com) by napolux | view | 0 comments
Next Token Prediction Is a Misleading Term
(boristhebrave.com) by ibobev | view | 0 comments
Cerebras – Faster Tokens Please
(newsletter.semianalysis.com) by pretext | view | 0 comments
Amazon employees are "tokenmaxxing" due to pressure to use AI tools
(arstechnica.com) by Bender | view | 0 comments
Show HN: Reducing LLM input tokens by 70%
(adola.app) by Jbunga | view | 0 comments