> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# Claude's Newest Models Stumble on Tool Calling, Raising Training Trade-offs
- URL: https://adjacent.media/signals/claudes-newest-models-stumble-on-tool-calling-raising-training-trade-offs/
- Published: 2026-07-06T16:07:31.000Z
- Updated: 2026-07-06T16:07:31.000Z
- Description: Anthropic’s latest Claude versions (Opus 4.8 and Sonnet 5) show degraded performance on tool-calling tasks—a critical capability for agents and integrations—likely because post-training optimized for Claude Code environments rather than general API consumers.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, model capability, llm performance, tool use

Source: [Pocoo](https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/?ref=adjacent.media)

Anthropic's latest Claude versions (Opus 4.8 and Sonnet 5) show degraded performance on tool-calling tasks—a critical capability for agents and integrations—likely because post-training optimized for Claude Code environments rather than general API consumers. Gains in one domain (sandboxed code execution) erode capabilities in another (flexible external tool use), forcing companies to choose their optimization targets. For developers building agent systems, model selection increasingly depends on the harness you're building.