Skip to content
Sign in
Artwork for Merge Conflict
Merge Conflict · June 1 · 34 min

517: Plan First, Think Less: Save Tokens, Improve Code

Episode 517 starts with a light chat about AI avatars and new text‑to‑speech deepfakes before diving into LLM “thinking” modes—what baked‑in planning actually does, why it multiplies token costs, and when it helps or hurts. James and Frank give concrete dev advice: try low‑thinking settings, use big models for creative planning then smaller ones to execute, leverage harnesses/system prompts, and beware quantized local models often do better without thinking. Follow Us Frank: Twitter, Blog, GitHub James: Twitter, Blog, GitHub Merge Conflict: Twitter, Facebook, Website, Chat on Discord Music : Amethyst Seer - Citrine by Adventureface ⭐⭐ Review Us ⭐⭐ Machine transcription available on http://mergeconflict.fm Support Merge Conflict

0:00 · Intro & Deepfakes-34:49
Play in
Transcript file

transcript

No transcript — this publisher did not publish one.

show notes

Episode 517 starts with a light chat about AI avatars and new text‑to‑speech deepfakes before diving into LLM “thinking” modes—what baked‑in planning actually does, why it multiplies token costs, and when it helps or hurts. James and Frank give concrete dev advice: try low‑thinking settings, use big models for creative planning then smaller ones to execute, leverage harnesses/system prompts, and beware quantized local models often do better without thinking.

Follow Us

⭐⭐ Review Us ⭐⭐

Machine transcription available on http://mergeconflict.fm

Support Merge Conflict

links13

chapters

6 chapters

more episodes

All episodes