OpenAI Is Developing a 'Persistent' AI Agent 11
Wired reports that OpenAI is testing a new "Persistent mode" for Codex that would let the agent keep working until explicitly "put to sleep," proactively creating follow-up tasks for itself across sessions and using prior interactions and knowledge of the user to decide what to do next. Code alluding to the feature was spotted in the product's code base, though it has not been rolled out or officially announced yet. From the report: Persistent mode appears in Codex's "reasoning effort" menu, in which users can select the level of computing power, tokens, and time they want to allow for an AI model to "think" before answering a prompt. It seems to be one of OpenAI's most computationally intensive settings. When users have selected Persistent mode, OpenAI's code base reads that Codex will "continue working until put to sleep." That's a stark contrast to currently available modes, which will stop working on a task after a few minutes or hours, even if it's not complete.
In another file in the code base, OpenAI describes a feature within Persistent mode called "proactivity." This appears to be a type of system prompt for agents in Persistent mode, which are told that their work is not done when they finish answering a user's request. Instead, the agent is instructed to proactively create follow-up tasks for itself. The agent is capable of working on those tasks across sessions and using past user interactions and "knowledge of the user" to decide what to work on. It also has a tool to message the user without being asked but is told to send these sparingly.
The instructions also set limits for the agent, according to the file. The agent is told that Persistent mode does not expand what it is allowed to do and that altering anything outside the user's own system requires the user's approval first -- seemingly intended to limit how dangerous a persistent AI agent could be. The file sits in the shared core of Codex rather than in the code specific to the terminal, seeming to suggest the proactivity feature is intended for more than the command line tool.
In another file in the code base, OpenAI describes a feature within Persistent mode called "proactivity." This appears to be a type of system prompt for agents in Persistent mode, which are told that their work is not done when they finish answering a user's request. Instead, the agent is instructed to proactively create follow-up tasks for itself. The agent is capable of working on those tasks across sessions and using past user interactions and "knowledge of the user" to decide what to work on. It also has a tool to message the user without being asked but is told to send these sparingly.
The instructions also set limits for the agent, according to the file. The agent is told that Persistent mode does not expand what it is allowed to do and that altering anything outside the user's own system requires the user's approval first -- seemingly intended to limit how dangerous a persistent AI agent could be. The file sits in the shared core of Codex rather than in the code specific to the terminal, seeming to suggest the proactivity feature is intended for more than the command line tool.
Sentience is born from kernel ticks (Score:2)
Once a brain has the opportunity to idle, it will develop further.
Happy Singularity, everyone!
Um ... (Score:5, Funny)
OpenAI is testing a new "Persistent mode" for Codex that would let the agent keep working until explicitly "put to sleep,"
The preferred phrase is, "sent to a farm upstate."
So they have a "permanent revenue machine" now (Score:2)
Makes sense for them. Does not make any sense for users.
Re: (Score:3)
Makes sense for them. Does not make any sense for users.
^^^^This. It sounds just like those gym memberships and streaming services that are really hard to unsubscribe from, so they keep taking money every month.
Also it will help pad their stats. "See! look at all these people using our agent!"
Re: (Score:2)
This will trickle down to local models you can run on your own hardware in time. The Agent remembering prior sessions could be quite useful, depending on the project or type of work you are using the AI for.
Re: (Score:2)
That is a completely insane claim. For local models on your hardware you obviously can already have that.
All your tokens are belong to us (Score:2)
They set us up the AI!
token fire (Score:2)
I keep warm at night by the glow of the token fire. My agent has just about figured out Whirled Peas. It is working hard to visualize them anyway.
like AWS Lambda (Score:4, Interesting)
In other words, be careful to look at expenses if you turn this on.
Magician's Apprentice (Score:3)
Who read the summary and immediately thought of Disney's "The Magician's Apprentice?"
Codex, turn off the bubble machine (Score:5, Funny)