Source link

OpenAI has introduced a new Developer mode for ChatGPT, giving users full access to the model context protocol (MCP) client across all tools. The feature, currently in beta, is available to Plus and Pro subscribers on the web.

According to OpenAI, the Developer mode enables both read and write capabilities for connectors, but also carries risks. “It’s powerful but dangerous and is intended for developers who understand how to safely configure and test connectors,” the company said in its guidance.

Users can enable the feature through Settings → Connectors → Advanced → Developer mode. Once active, developers can import MCPs by adding a remote MCP server in the Connectors tab. Supported protocols include SSE and streaming HTTP, with OAuth or no authentication options.

The feature allows developers to manage tools directly from connectors. They can toggle tools on or off, refresh connector data and use custom prompting to call specific tools in conversations. OpenAI cautions that careful tool selection is required to avoid ambiguity or misuse.

“Be explicit: ‘Use the Acme CRM connector’s update_record tool to…’,” the company advised, noting that developers should also specify sequencing of tool calls and state preferences when multiple connectors overlap.

Write actions triggered through Developer mode require user confirmation. OpenAI recommends closely inspecting JSON payloads before approval. “Incorrect write actions can inadvertently destroy, alter or share data,” the company warned.

The system respects the readOnlyHint annotation, treating tools without it as write actions. Users can choose to remember approval or denial for tools within a conversation, though OpenAI emphasised that such trust should be granted only to reliable applications.

Developer mode also provides visibility into tool input and output data, enabling debugging and verification of tool behaviour.

The post OpenAI Rolls Out Developer Mode in ChatGPT With Full MCP Access appeared first on Analytics India Magazine.

Source link

OpenAI has struck one of the largest cloud computing deals in history with Oracle, agreeing to a contract worth about $300 billion over five years starting in 2027. 

According to the Wall Street Journal, the agreement will see Oracle supply OpenAI with roughly 4.5 gigawatts of computing capacity, an amount of power comparable to two Hoover Dams or enough to run around four million homes.

The scale of the deal is staggering compared to OpenAI’s current business. The AI company generates around $10 billion in annual revenue, making the long-term commitment a major financial bet on the future of its technology. 

For Oracle, the agreement represents a transformative moment. Shares of the company surged by nearly 43%  following the announcement, the biggest single-day gain since 1992. The stock jump added more than $100 billion to Chairman Larry Ellison’s wealth, briefly pushing him past Elon Musk and Jeff Bezos in global rich lists.

Still, both sides face significant risks. For OpenAI, the multi-hundred-billion-dollar commitment locks the company into massive infrastructure spending far outpacing its current revenues. 

For Oracle, delivering on such a colossal supply of cloud and AI infrastructure may require heavy investment and debt financing, while tying its fortunes closely to one customer.

The deal also carries major strategic implications. OpenAI has long relied on Microsoft’s Azure cloud, but working with Oracle shows it is diversifying its computing needs. 

The partnership also ties into “Stargate,” a massive AI infrastructure project backed by Oracle, SoftBank and others, aimed at powering the next generation of large-scale AI systems.

Ultimately, the agreement highlights how the race to lead in AI is now driven by huge bets on infrastructure. For Oracle, the win boosts its position against Microsoft, Amazon and Google in the cloud market.

The post Oracle Lands $300 Billion OpenAI Cloud Deal, One of the Largest in History appeared first on Analytics India Magazine.

Source link