Glean 拾遗
Daily · timeline

A few picks a day.

Fri, Jul 17, 2026 3picks
← 07-16
Calendar ▾
2026 · 07
MoTuWeThFrSaSu ··12345678910111213141516171819202122232425262728293031
has picks today
06:00

Cut Claude Code token costs by rendering system prompts & history as images

将文本上下文渲染为图片,本地代理为 Claude Code 削减约 60% token 成本

pxpipe is a local proxy that intercepts Claude Code API requests, rendering bulky text parts like system prompts, tool docs, and old history into compact PNG images. Since image token pricing depends on pixel dimensions rather than text length, the approach cuts input tokens by ~60%, leading to a 59–70% end-to-end cost reduction. It rewrites requests before they leave the machine, preserving prompt caching. By default it works with Claude Fable 5 and GPT-5.6, with dashboard controls for opt-in models. It includes profitability gates and benchmarks showing near parity in coding tasks, though exact-string recall is lossy. The project is aimed at developers using LLM coding agents who want to slash API costs without sacrificing functionality.

github.com · 12 min · Ai Tooling · Anthropic · CLI · Developer Tools · LLM · Token-Optimization
06:00

The Short Leash AI Coding Method For Beating Fable

「短绳」编程法:人类把关,AI编码质量胜过Fable

This post distills over a year of research on using AI agents for security-critical software. The author introduces the “Short Leash” method: only expert developers can use it; never enable YOLO mode; manually review every diff in the permissions prompt to keep the AI on track; commit after each subtask to safeguard against regressions. It also details AI-assisted code review: pair human and AI, with AI catching surface errors and humans guiding direction. PR authors must self-review line-by-line and disclose AI models used. This approach beats Fable even with non‑frontier models, without sacrificing quality. Targeted at senior engineers who want productivity gains without giving up understanding.

blog.okturtles.org · 7 min · AI Agents · AI Engineering · Code · Code Review · Developer Tools
06:00

Better Models: Worse Tools

模型越强,工具越差:Anthropic 新模型为何在第三方编辑工具上表现倒退

Armin reports a counterintuitive bug encountered while developing Pi code editor: newer Claude models, including Opus 4.8 and Sonnet 5, invent extra fields in the nested edits[] array when calling Pi's custom edit tool, causing the tool call to be rejected. Older Claude models do not exhibit this behavior. Armin hypothesizes that Anthropic's reinforcement learning has specifically optimized newer models for Claude Code's built-in edit tool, inadvertently degrading performance on other tool schemas. The piece questions whether third-party coding harnesses must implement multiple edit tools per model family, and highlights the fundamental trade-off between specialized training and general tool compatibility.

simonwillison.net · 2 min · Agent Engineering · AI Engineering · Claude Code · LLM · Tool Use