🎧 START pod: Tejas Bhakta, Founder & CEO , Morph "Subagents and tools that improve coding agents"
START · Fondo
Audio is streamed directly from the publisher (media.transistor.fm) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
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