TypeSafe AI launched Jev, a 40B-parameter "System One" transformer trained exclusively on synthetic data via RLCD that returns typed values with calibrated probabilities instead of free text, in early…
Fin's 2x Team published a set of context-management practices for Claude Code sessions, arguing that keeping starting context small and pruning stale memory directly lowers token costs and improves ou…
A developer's Claude Code subagent harness routes planning and final review to Fable while delegating execution to Opus, Sonnet and Haiku, after a June workflow script with a single model-less agent()…
A developer published a subagent configuration that automates web browsers through the agent-browser CLI, driving navigation, clicking, form filling, screenshots and snapshots over a Chrome DevTools P…
A developer measured Claude Code's new `claude plugin eval` tool against 89 skill directories in a coffee e-commerce project, finding that trigger rates for positive test cases fell from 100% with a s…
Polish developer Jock's experiment running 255 AI agents across three pipelines to produce the same graphic novel found that the first version — 50 pages drawn by 50 Sonnet agents in 30 minutes using …
TypeSafe released jev-pilot, a Claude Code plugin that queries the company's fast decision model Jev before every turn to set reasoning effort from low to xhigh, pick a subagent model (Haiku, Sonnet o…
Three OSLabs engineers built PennyWyze, an open-source CLI that audits which Claude tier — Opus, Sonnet, or Haiku — is the cheapest that still meets a user-defined accuracy bar, pricing every call fro…
Three OSLabs engineers built PennyWyze, an open-source CLI that audits whether a production prompt can run on a cheaper Claude tier without dropping below a user-defined accuracy bar. The tool runs a …
A developer has proposed a role-based model routing system for AI coding sessions, assigning tasks to Navigator, Builder, Diagnostician, or Surgeon roles based on the cost of feedback rather than proj…
A backend developer argues that 27-30 billion parameter open-weight LLMs handle most Go backend development tasks, including security redteaming, without the cost or refusals of frontier models from O…
A developer's analysis of Claude Code's configuration files, environment variables, and API network traffic found that several default features silently inflate token costs, including background sessi…
A developer built an open-source Codex skill, Astra Flash Orchestrator, that routes high-volume coding work to DeepSeek V4.1 Flash while reserving the pricier Astra model for planning, architecture, a…
A developer who has spent over $30,000 on tokens across Codex, Claude, and GLM since the start of the year argues that large language models now fall into two categories: instruction-following models …
A developer's experiment running 800 Claude coding sessions across 20 programming languages found that terse array languages like K, Uiua, APL and BQN did not dominate token efficiency, with Ruby, Pyt…
A developer has published a global Claude Code configuration file (~/.claude/CLAUDE.md) that codifies standing rules for AI coding agents, including one git commit per completed task, explicit model-t…
A new 18-chapter book, "Claude Code from Source," reverse-engineers Anthropic's Claude Code AI coding agent from the TypeScript source maps that shipped with the tool on npm, which included a sourcesC…
Users of the Assistant product reported that reasoning models disappeared from the model picker, with one ultimate subscriber saying they could no longer select Sonnet with reasoning. A respondent sai…
Anthropic introduced Claude Tag, a new Slack integration that lets teams add Claude as a team member in selected channels and tag @Claude to delegate tasks, with the Sonnet model powering it. Users ca…
A developer using Claude Code on a Max subscription documented how making the top model (Fable) the session default caused built-in skills like /code-review and /simplify to inherit that model and exh…