Subconscious and GLM-5.2 Makes "/compact" Obsolete

Name: Subconscious and GLM-5.2 Makes "/compact" Obsolete
Availability: InStock
Author: hyluo

by hyluo·Jun 22, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●MidBold Bet

Another context management pitch when Cursor and Continue already solve this.

Strengths

•Auto-compaction without manual triggers addresses real agent workflow friction.
•TIMRUN inference system claims optimization specifically for agentic workloads.

Weaknesses

•Blog post format with marketing language lacks verifiable technical implementation details.
•No benchmarks, code samples, or comparison data to validate the performance claims.

Post Description

GLM-5.2 is a turning point for coding agents. It's the first model a business would actually pay to replace Claude Opus with. We gave GLM-5.2 the ability to control its own context during agentic tasks, and paired it with Subconscious Cache — ensuring reliable long-term memory far beyond the context window.

This blog post walks through our approach to long-horizon agents, long-context LLMs, harness-driven context management, and our model-driven context state compression.

Try GLM-5.2 hosted by Subconscious.dev using the examples in the post. The model keeps running until the message list outgrows your internet connection where your WiFi becomes the bottleneck before context window.