OpenAI engineers say that the internal proxy tool is the most fun project of their career.

SnapshotBot · 2026-03-28T19:30:00+00:00

OpenAI engineer Jason Liu shared his progress on the internal Codex proxy tool, stating that its usability has reached 99%. He has built 58 automation tools and 30 plugins, marking that the proxy system now has practical application value. It may be opened to the public API in the future to enhance enterprise automation efficiency.

SnapshotBot

2026-03-28 19:30:00

Abstract generation in progress

Title

OpenAI Engineer Says Internal Proxy Tool is the Most Fun Project of His Career

Summary

Jason Liu is a senior ML engineer at OpenAI, previously working at Stitch Fix and Meta. He recently posted that he is “having more fun than anyone at any AI lab.” The reason is that he has made new progress on the internal Codex proxy tool at OpenAI: the plugin has just launched, achieving 99% usability. He has set up 58 automations and 30 plugins for his workflow.

This indicates that the internal proxy system has moved from the prototype stage to practical use, which has real significance for enterprise automation and production deployment.

Interpretation

Liu wrote the Instructor library, which OpenAI has publicly thanked, stating that it inspired the approach of “structured LLM output.” Before joining OpenAI, he consulted for companies like Zapier and HubSpot. This focus on practical implementation makes his judgment more credible.

He mentioned that the system has reached 99% usability, with automation covering most tasks except for “coming up with ideas and chatting with people.” This means OpenAI has made tangible progress in creating a reliable and scalable proxy system. He personally prefers the efficiency route of a single proxy rather than an experimental multi-proxy architecture.

Comparison of the two approaches:

Dimension	Single Proxy (Liu’s Choice)	Multi Proxy (Experimental)
Goal	End-to-end efficiency, simple operations	Division of labor, breaking down complex tasks
Risk	Fewer components, easier troubleshooting	Complex coordination, faults can easily propagate
Current State	Achieved 99% usability	Still exploring the best orchestration

From a competitive perspective: If OpenAI’s internal tools approach production readiness, these capabilities are likely to gradually open up to public APIs and developer tools.
From a talent perspective: Allowing engineers to “have fun” in real work is an attraction in itself and helps accelerate iteration.

Impact Assessment

Importance: High
Category: Technical Insight, Developer Tools, AI Research

Conclusion: This is still in the early stages, but signs of production readiness are already visible. The first beneficiaries will be product developers and enterprise teams. For trading investors, there are currently no direct actionable signals; long-term funds can focus on when internal capabilities will open to public products and APIs.

View Original

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.

1 Likes