Observation: Models Differ Wildly in Tool-Call Intermediate Steps
DanielLockyer · x · 2026-09-21
Developer Daniel Lockyer notes that different models take noticeably different approaches to tool calls and intermediate processing—some write bash scripts, others prefer Python. A one-line observation without further detail.
More from Models
- Tuned 26B diffusion model beats Jev after adding 512-token decode-time reasoning budget — rickasaurus · 2026-09-21
- Users Report Opus 5 Feeling Suspiciously Faster and Better Inside Claude Code — rudrank · 2026-09-21
- Hemmingway-1: Apache-2.0 27B writing-only model scores 1330 on EQ-Bench 4, beats GPT-5.5 — Lukinator6446 · 2026-09-21
- Astra is terrified of mistakes — humans may still own high-entropy decisions — xiaosun86 · 2026-09-21
- Inspired by Jev, developer builds Vector, a general action model — BLUECOW009 · 2026-09-21
- Sentdex softens on Jev: solid LLM augmentation saving tokens per iteration — Sentdex · 2026-09-21