Subbu Athikunte

Chief AI Engineer @ DigitalApi

[Subbu Athikunte @athikunte]

I have been using Codex a little differently this week.

Earlier, I would ask one agent to do a task, then I would review the output myself.

- This time, I kept one thread as the orchestrator.
- Then I used separate threads for the work.
- One thread made the PR.
- Another thread reviewed the PR.
- The first thread fixed the review comments.
- The review thread checked it again.
- Only after that did the orchestrator move to the next piece.

this is "loop engineering" within codex.

The prompt is only the start.
The useful part is the loop around the work.
Who owns the task?
Who reviews it?
What happens when the review finds a problem?
When is the work done?
When should the human step in?

This is the part that makes multi-agent work useful for engineering.
Starting agents is easy.
Closing the loop is the hard part.

[Subbu Athikunte @athikunte]

I managed to get the loop working from inside codex. It created 7 threads and acted as an orchestrator to manage and reconcile PRs at the end. pure magic

[Theo - t3.gg @theo]

If you're curious how I managed to do over $20,000 in inference on the last 48 hours, here's a video all about it.

Spoiler: loops are really powerful

[Subbu Athikunte @athikunte]

@jxnlco Talk to your UI and get the work done instead of clicking around and typing. This is a complex UI of an mcp gateway. Voice assistant just makes it a no-brainer.

[Subbu Athikunte @athikunte]

@_lopopolo I have setup a operational harness for my project that runs in k8s. It connects and does all kinds of diagnosis working across logs, db, pods. It keeps making notes using your MLD framework. refining its own methods. Not having to navigate kubectl has been huge time saver.

[Subbu Athikunte @athikunte]

@alexgilev @AgenticUi @alexgilev I preordered AgenticUI and haven't received the Figma updates. I tried out to you on email and DM multiple times but no response. Pls help

[Subbu Athikunte @athikunte]

My codex usage

[Subbu Athikunte @athikunte]

How do you setup a large number of MCP servers to test a MCP gateway? MCP Zoo. I just built a mock server that mimics different properties of these servers. To make it fun to use I just got gpt-image-2 to generate a nice image.

Day 10: Enterprise MCP Gateway development

[Subbu Athikunte @athikunte]

@daniel_mac8 @ExplicitMbuwa You can build the first version in Codex, give both source code and the paper to Pro to optimize/improve it. Best of both worlds.

[Subbu Athikunte @athikunte]

Using Codex to drive Claude. Claude acts as UI engineer and Codex the tester.

Day 9: Enterprise MCP Gateway development

[Subbu Athikunte @athikunte]

Day 8 - Designing Enterprise MCP Gateway

I have been using OpenAI's symphony to develop the mcp gateway. This is the current session. Codex app server spinning up 5 codex sessions in parallel to implement 5 todo's from the Linear board.

[Subbu Athikunte @athikunte]

Day 7 - Designing Enterprise MCP Gateway

High level architecture

[Subbu Athikunte @athikunte]

This is really good with Indian languages. "create the front page of a Hindi newspaper dated May 13, 2023" picked up news from that day and created an image. Very impressive.

[OpenAI @OpenAI]

Stronger Across Languages

ChatGPT Images 2.0 can produce images with non-English text that’s not only rendered correctly but with language that flows coherently.

This makes the model more globally useful and helps people create visuals that work in the languages they actually use.

[Subbu Athikunte @athikunte]

Finally hit the limits of a $200 pro plan in codex. 23 hours of continuos run. Multiple auto compacts. Surprisingly, codex doesn't stop mid session even when its out of messages.

[Lenny Rachitsky @lennysan]

"Using coding agents well is taking every inch of my 25 years of experience as a software engineer, and it is mentally exhausting.

I can fire up four agents in parallel and have them work on four different problems, and by 11am I am wiped out for the day.

There is a limit on human cognition. Even if you're not reviewing everything they're doing, how much you can hold in your head at one time. There's a sort of personal skill that we have to learn, which is finding our new limits. What is a responsible way for us to not burn out, and for us to use the time that we have?" @simonw

[Subbu Athikunte @athikunte]

@sean_moriarity Is there a way to use ChatGPT Pro subscription instead of OPENAI_API_KEY?

[Paras Chopra @paraschopra]

We made LLMs speak Tulu, a language with only 2 million speakers.

It wasn't easy because LLMs kept confusing it with Kannada, but we discovered negative constraints really help.

[Subbu Athikunte @athikunte]

@gochaberulava I ask codex to tail the server logs. they use my ssh or fly logs if deploying to fly. it uses background agents to do this.

[Subbu Athikunte @athikunte]

@IntuitMachine do you have this in article format?

[Subbu Athikunte @athikunte]

@BenCarr630567 CARA

[Subbu Athikunte @athikunte]

I am using codex to do blue/green deployments. It's also pretty good to learn/refresh learning. ServerOps and DevOps with either Claude/Codex is really good.