@charliermarsh: Since my last post, I reduced ty’s retained memory by another 15% with Codex. We're now at a ~25% memory reduction over…

X AI KOLs Following News

Summary

Developer @charliermarsh reports reducing ty's retained memory by another 15% using Codex, achieving a total ~25% memory reduction via /goal, and expresses enthusiasm for GPT models.

Since my last post, I reduced ty’s retained memory by another 15% with Codex. We're now at a ~25% memory reduction overall via /goal, largely in the background. I love working with the GPT models so much. https://t.co/YzTJ6LyZp8
Original Article
View Cached Full Text

Cached at: 06/09/26, 02:53 PM

Since my last post, I reduced ty’s retained memory by another 15% with Codex. We’re now at a ~25% memory reduction overall via /goal, largely in the background.

I love working with the GPT models so much. https://t.co/YzTJ6LyZp8

Similar Articles

@ashwingop: https://x.com/ashwingop/status/2065080505113125105

X AI KOLs Timeline

Sentra's Code Memory system boosts GPT-5.5 to 88.31% on Terminal-Bench 2.1 at a quarter of the cost, outperforming Anthropic's restricted Mythos 5 model. The memory layer reduces input tokens by 52% and costs by 72.6% while improving task success rates.

@billtheinvestor: Give Claude Code and Codex infinite memory, programming efficiency improved by 92%! The Agentmemory tool has quickly gained 4000+ stars on GitHub and is completely free. It saves all information from your coding sessions through smart compression, and automatically extracts relevant context in future sessions, avoiding re...

X AI KOLs Timeline

Agentmemory is an open-source tool that provides infinite memory for Claude Code and Codex, reducing token usage through intelligent compression, improving programming efficiency, and has gained 4000+ stars on GitHub.

Building more with GPT-5.1-Codex-Max

OpenAI Blog

OpenAI introduces GPT-5.1-Codex-Max, a new agentic coding model with improved reasoning, token efficiency, and the ability to maintain coherent work across millions of tokens through a 'compaction' mechanism. The model is faster, more intelligent, and can sustain long-running tasks for hours or days, representing a significant advancement in AI-assisted software engineering.