---
title: "Frontier models for the hard parts, open weights for the rest"
category: "talks"
date: "2026-06-29"
time: "11:10am-11:30am"
track: "Expo Stage 3 SW"
room: "Expo Stage 3 SW"
speakers: []
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: ""
scheduleRoom: "Expo Stage 3 SW"
scheduleLabels: ["Expo Stage 3 SW", "session", "confirmed"]
---
# Frontier models for the hard parts, open weights for the rest

## Conference Context
- Date/time: 2026-06-29 · 11:10am-11:30am
- Track/room: track TBD · Expo Stage 3 SW
- Speaker(s): TBA
- Session type/status: session · confirmed

- Track: track TBD
- Room: Expo Stage 3 SW
- Session type: session
- Status: confirmed

## Session Description
Kimchi is an open-source coding agent that orchestrates multiple AI models—including open-weight models like Kimi K2.7 and MiniMax M3 alongside commercial frontier models—to intelligently route each task to the best model for the job. Powered by Ferment, Kimchi evaluates every step, automatically reworking or escalating tasks when needed to maintain quality while minimizing the use of expensive frontier models. The result is high-quality code generation at approximately 2.5x lower cost than relying on commercial models alone—all with the transparency and flexibility of open source.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# Frontier models for the hard parts, open weights for the rest ## Conference Context - Date/time: 2026-06-29 · 11:10am-11:30am - Track/room: track TBD · Expo Stage 3 SW - Speaker(s): TBA - Session type/status: session · confirmed - Track: track TBD - Room: Expo Stage 3 SW - Session type: session - Status: confirmed ## Session Description Kimchi is an open-source coding agent that orchestrates multiple AI models—including open-weight models like Kimi K2.7 and MiniMax M3 alongside commercial frontier models—to intelligently route each task to the best model for the job. Powered by Ferment, Kimchi evaluates every step, automatically reworking or escalating tasks when needed to maintain quality while minimizing the use of expensive frontier models. The result is high-quality code generation at approximately 2.5x lower cost than relying on commercial models alone—all with the transparency and flexibility of open source. ## Media Evidence No related AI Engineer channel video found yet.

### Speaker And Company Context
- No speaker profile is attached in the official schedule data.

### Topics Covered
- [[coding-agents]]

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.