token
34 stories and discussions about token, aggregated from every source we track.
Generate fonts where every LLM token is the same width
AI-assisted development is rapidly moving beyond autocomplete and simple chat interfaces. We are...
Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts
Symmetric encryption over HTTPS: one bearer token, one call per operation, and no key rings or IAM policies to set up.
Strands harness is a fully assembled, customizable, state-of-the-art agent you run locally or deploy anywhere.
On-policy distillation (OPD) trains a student model by having it generate trajectories, then matching its next-token predictions with an external teacher's next-token predictions. This provides dense, token-level…
Claude spent 119,000 tokens to produce a 107-token program that didn't work, in a programming language that nobody uses? Or that the code you make with Claude is about 2% of your token spend? If so, read this.
Research on aligning AI with human values and intent, and reports documenting model failures.
Language through a fly’s wiring. A next-token experiment trained from scratch, with an inspectable brain and matched language benchmarks.
High-assurance in-memory Tree-Sitter AST context firewall and pruning MCP server for coding agents (-72.4% token mass). - heuristicolab/ctxfw
Vercel data shows downloadable-weight models processing 56% of production AI Gateway tokens in August, while capturing only 14% of spending.
Crypto tokens have become an important part of the Web3 ecosystem. Startups, DeFi platforms, gaming projects, businesses, and blockchain applications can use tokens for payments,... - Startup growth insights and…
Model providers now advertise context windows large enough to hold a codebase or a stack of contracts...
As the Industry Separates Prefill from Decode, Lumai Says the Next Step Is to Rethink the Compute Architecture Powering Each Stage AI infrastructure has spent the past several years optimizing for …
Students had one Friday evening, 18 GB of coding-agent transcripts, and a single question: where are we burning tokens? They found many wasteful patterns in agentic coding.
🪨 why input many code when few code do trick. Slashes input tokens by up to ~80% across 9 languages via AST pruning, ultra-dense "caveman" syntax and more for AI coding agents. - Grimm671...
Free CLI from Everest that compresses Codex tool output. - spenmcke/compress
How coding and legal agents use tokens across instructions, tools, reasoning, and skills.
I analyzed 1,674 agent sessions to reduce token usage in Claude Code, Codex, and Cursor. 10 rules and a hook fixed most of it.
The safety of a tool-using language model agent is usually treated as a property of the model alone. We give controlled, full-precision evidence that it is instead a joint property of the model and the software that…
Eaon Code — Eaon's official coding agent. Token-efficient, extensible, built atop the Pi harness. - eaonlabs/eaon-code
An SEO and Generative Engine Optimization (GEO) suite for Google Antigravity, powered by Go. - angelotc/antigravity-seo
A sideloaded package turns a Microsoft-signed binary into an OAuth token theft tool. No phishing domain, no spoofed UI, no browser. Here's how to detect it.
The September 2026 AI Gateway production index covering data from August 2026: Open-weight models took the majority of token volume for the first time ever; Fable loses two-thirds of its spend share and Opus 5 tripled…
Hiding a file inside a story, one token at a time.
Strands harness is a fully assembled, customizable, state-of-the-art agent you run locally or deploy anywhere.