A developer turned ChatGPT's unlimited chats into a free coding agent pool
I Am the Reason OpenAI Is Killing Unlimited Chats
By wiring Desktop Commander and a computer-use agent into ChatGPT through custom MCP servers and OpenAI's Secure MCP Tunnel, the author ran parallel coding agents on his own laptop and VPS — no paid API calls, no Codex limits. He split plans into GitHub issues, assigned each to a separate chat, and built a Windows tray dashboard to watch tool calls. Now that unlimited chats are ending, he's switching to Claude.
I am simply making the best use of what OpenAI has made available to me: ChatGPT conversations, MCP support, secure tunnels, and the ability to connect my own tools.
- thorncorona
> To be clear, I am not breaking any rules.
> I am simply making the best use of what OpenAI has made available to me
People like this are why you can't have good things.
- ronsor
I understand preferring Claude models in the abstract, but as a product? The random restrictions have significantly reduced their usability.
We had 2 major threads in the past 48 hours complaining about this:
* https://news.ycombinator.com/item?id=50319358 (AI/ML work with large models)
* https://news.ycombinator.com/item?id=50320255 (reverse engineering)
The threads are full of upset comments!
The only non-OAI options are open models and I guess Gemini 4 now.
- suyash
Click bait titles are trending on HN now?
- meisel
@dang can we change the title? It’s clickbait
- jasongi
While I'm sure OpenAI won't miss OPs business, the "Claude here I come" is pretty indicative of the value in subs at the moment.
Claude seems to have higher limits by default instead of playing the random reset games.
In a world where subscription value isn't obfuscated by unlimited chat, the choice for a power user is obvious, especially since it took a month after Sonnet 5.5 for OpenAI to get Terra 6.1 out, using Sol for everything just ate through the limits.