#Claude

sqlite-utils 4.0rc2, a release candidate for the popular SQLite database utility, has been released. The majority of the code changes in this release were written by Anthropic's Claude Fable AI model, costing approximately $149.25. This release demonstrates the growing capability of AI-assisted software development, as Claude Fable identified and fixed critical bugs like a data loss bug in deletewhere() that would have otherwise shipped. It shows that AI can not only write code but also perform code review that catches subtle, high-impact issues. The AI assistant conducted a review of the 4.0rc1 release and identified 5 release-blocking issues, including a severe data loss bug. Over 37 prompts, 34 commits, and +1321/-190 code changes across 30 files, the team worked through all feedback, with the AI generating most of the code and fixes.

Newer Claude models (Opus 4.8 and Sonnet 5) generate malformed tool calls that include extra invented fields, causing tool call rejections in third-party coding harnesses like Pi, while older models did not exhibit this issue. This counterintuitive regression shows that reinforcement learning for specific tool schemas can degrade performance on other tools, posing reliability challenges for developers building agents that rely on consistent tool-use behavior. The malformed calls typically have the correct edit content but include made-up keys in the nested edits[] array, violating the schema. Armin Ronacher hypothesizes that newer models are overtrained on Claude Code's built-in edit tool format.

Anthropic released Claude Sonnet 5 on June 30, 2026, claiming performance close to Opus 4.8 at lower prices, along with a system card detailing its safeguards. This release offers developers a more cost-effective alternative near the top-tier Opus performance, potentially accelerating adoption of Anthropic's models in applications requiring high intelligence. Sonnet 5 features a 1 million token context window, 128,000 output tokens, no longer supports sampling parameters like temperature, and uses a new tokenizer that increases token counts by about 30% for English, effectively raising prices despite unchanged per-token rates.