100 How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size arxiv.org · 1d 11h ago
100 TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models arxiv.org · 1d 11h ago
100 Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment arxiv.org · 1d 11h ago
100 Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale arxiv.org · 1d 11h ago
100 Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows arxiv.org · 1d 11h ago
41 Show HN: Track Token usage for major platforms,know your token flow lifehacksgermany.com · 20h 33m ago
100 CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations arxiv.org · 3d 11h ago
100 EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction arxiv.org · 5d 11h ago
100 Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models arxiv.org · 9d 9h ago
100 Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning arxiv.org · 9d 9h ago
100 QuechuaTok: Morphological Boundary Accuracy as a Necessary Metric for Tokenizer Evaluation in Agglutinative Low-Resource Languages arxiv.org · 10d 11h ago
100 Toten: Knowledge-Based Ontological Tokenization Of Physical Quantities And Technical Notation In Brazilian Portuguese arxiv.org · 15d 11h ago
100 BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation arxiv.org · 15d 11h ago
100 Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning arxiv.org · 15d 11h ago
100 Self-Generated Error Training for Token Editing in Diffusion Language Models arxiv.org · 17d 11h ago
100 EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction arxiv.org · 5d 11h ago
100 Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models arxiv.org · 9d 9h ago
100 Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning arxiv.org · 9d 9h ago
42 Earned vs. Burned, Claude skill for measuring AI delivery value (not tokens) github.com · 4d 16h ago
42 Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Trac arxiv.org · 8d 9h ago
42 Tokenmaxxing is dead, and the real AI cost reckoning hasn’t started yet mimetiq.substack.com · 9d 2h ago
42 Halyard – open AI work ledger for developers (time, tokens, cost, invoices) github.com · 9d 15h ago
41 NSA’s SIGINT Enabling Project includes sabotaging cryptographic standards nsa.2026.action.cr.yp.to · 6d 18h ago
41 Michael Saylor’s Strategy has no easy way out as Bitcoin prices continue to drop finance.yahoo.com · 7d 4h ago
40 Show HN: Verigate – Cryptographic authorization receipts for AI agents verigate.cloud · 5d 22h ago
40 ’Crypto vs. community’: local US lenders join forces to fight ’stablecoins’ law theguardian.com · 6d 1h ago
40 Implementing CRYSTALS-Kyber (post-quantum cryptography) from scratch in Python jani.isohanni.fi · 9d 1h ago
39 Breaking the Tokenizer Barrier: On-Policy Distillation Across Model Families arxiv.org · 5d 12h ago
38 Transfer events can lie, storage cannot: catching malicious token transfers functori.com · 9d 2h ago
37 Show HN: A site that emails you the day your Bitcoin stack hits $1M amimillionaire.com · 5d 15h ago
37 Study: Governed AI retrieval – 97% pass rate, 67% fewer tokens (Emory, IBM) promptowl.ai · 8d 20h ago