Episode
🎧 START pod: Tejas Bhakta, Founder & CEO , Morph "Subagents and tools that improve coding agents"
- Podcast
- START
- Published
- Mar 27, 2026
- Duration seconds
- 1215
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/9464f985
Actions
POST https://stenobird.com/v1/public/podcasts/start-7171926/episodes/start-pod-tejas-bhakta-founder-ceo-morph-subagents-and-tools-that-improve-coding-agents/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/start-7171926/start-pod-tejas-bhakta-founder-ceo-morph-subagents-and-tools-that-improve-coding-agents.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
Agents don’t need bigger models. They need better tools. Morph trains coding subagents. Not for humans. For frontier models. Fast Apply edits at 10,000 tokens/sec . WarpGrep handles code and log search. Both keep the main model’s context clean Because when context gets too large, performance drops. Now Morph is pushing coding subagents even faster. One newer model runs at 33,000 tokens/sec: https://docs.morphllm.com/sdk/components/compact 🎙️ Tejas Bhakta, Founder & CEO, Morph 01:30 Fast Apply + WarpGrep 02:26 Context fills up around 100k 02:38 Keep the main model context clean 03:31 “You can’t scale human attention 100x” 07:28 Founders are missing how to value human attention 08:30 New model at 33,000 tokens/sec 10:08 Better, faster, and cheaper than the frontier