OpenAI Codex Updates and Agent API Updates : Now Available for Plus Users
OpenAI has announced new updates to its Codex and its Agent API, enhancing accessibility, functionality, and safety for developers. These updates include expanded access to Codex, new internet-enabled capabilities, improved agent development tools, and advancements in voice agent technology.
OpenAI's Codex, an AI-powered tool designed to generate and execute code, is now available to a broader audience. Previously limited to Enterprise, Team, and Pro users, Codex has been extended to ChatGPT Plus subscribers. This move aligns with OpenAI's mission to provide widespread access to advanced AI tools, allowing a wider range of developers to use its capabilities for diverse applications.
Key improvements to Codex include the introduction of controlled internet access during task execution. This feature allows developers to perform tasks such as installing dependencies, testing scripts that require staging servers, and executing complex workflows. To address potential risks, internet access is disabled by default and governed by strict safeguards, including:
– Domain restrictions to limit access to specific websites.
– HTTP method limitations to control the types of requests made.
– Prompt injection monitoring to detect and mitigate malicious inputs.
These measures ensure that developers can innovate securely while maintaining control over their environments, balancing functionality with safety. Agent API and SDKs: New Tools and Real-Time Capabilities
The Agent API has undergone substantial upgrades, particularly in its development tools. The Agents SDK now supports TypeScript, achieving parity with the existing Python SDK. This addition broadens the programming options available to developers, making it easier to create AI agents with advanced features such as:
– Handoffs for seamless transitions between automated and human interactions.
– Guardrails to enforce safety and compliance.
– Tracing for monitoring agent activity.
– Human-in-the-loop approvals to allow human oversight during critical decision-making processes.
These tools streamline the development process, allowing faster and more secure deployment of AI agents across various industries.
One of the most notable updates is the introduction of the RealtimeAgent feature. This capability allows developers to build voice agents that operate in real time, either on the client or server side. RealtimeAgents come equipped with advanced functionalities, including:
– Automated tool calls to perform tasks dynamically.
– Safety guardrails to prevent misuse and ensure ethical operation.
– Seamless handling of audio input/output and interruptions for smoother interactions.
By integrating these features, the RealtimeAgent enhances the practicality and reliability of voice-based AI systems, opening up new possibilities for real-world applications such as customer service, virtual assistants, and accessibility tools. Watch this video on YouTube. Monitoring and Managing AI Agent Performance
To help developers optimize the performance of their AI agents, OpenAI has introduced the Traces Dashboard. This tool provides a detailed visualization of Realtime API sessions, offering insights into key metrics such as:
– Audio input/output performance.
– Tool usage during interactions.
– Interruptions and how they are handled.
By giving developers a clear view of agent performance, the Traces Dashboard helps identify and address potential issues, making sure smoother operation and improved outcomes. This level of transparency and control is particularly valuable for developers working on complex or high-stakes applications.
Additionally, the Speech-to-Speech model has been updated to improve its reliability in areas such as instruction following, tool calling, and handling interruptions. The latest version, `gpt-4o-realtime-preview-2025-06-03`, is now available through both the Realtime API and Chat Completions API. These updates enhance the model's ability to assist seamless voice-to-voice communication, further expanding its utility in diverse scenarios, including multilingual communication and real-time translation. Safety and Oversight: A Core Priority
Safety remains a cornerstone of OpenAI's approach to AI development. The latest updates include robust guardrails designed to prevent misuse and ensure ethical operation. Key safety measures include:
– Prompt injection monitoring to protect against malicious inputs that could compromise system integrity.
– Human-in-the-loop mechanisms to allow human operators to intervene when necessary, adding an extra layer of oversight.
– Domain and method restrictions to limit the scope of internet access and reduce potential vulnerabilities.
These safeguards reflect OpenAI's dedication to responsible AI deployment, balancing innovation with accountability. By prioritizing safety, OpenAI aims to build trust in its technologies while allowing developers to explore new possibilities with confidence. Advancing AI Development with Practical Applications
The updates to OpenAI's Codex and Agent API represent a significant advancement in the field of AI technology. By broadening access to Codex, introducing real-time capabilities through the RealtimeAgent, and enhancing safety mechanisms, OpenAI continues to empower developers to create innovative solutions. These tools are designed to address the challenges of integrating AI into practical applications, offering developers the resources they need to build systems that are both effective and responsible.
The combination of expanded functionality, real-time interaction capabilities, and robust safety measures positions OpenAI's tools as valuable assets for developers across industries. Whether used for automating workflows, improving customer interactions, or allowing accessibility, these updates highlight the growing potential of AI-driven solutions to address real-world needs.
By focusing on accessibility, functionality, and safety, OpenAI sets a benchmark for responsible AI development. These updates not only expand the potential of AI technologies but also underscore the importance of ethical considerations in their deployment. As AI continues to evolve, tools like Codex and the Agent API will play a critical role in shaping the future of technology and its applications. Advance your skills in AI code generation. by reading more of our detailed content. Filed Under: AI, Top News
Latest Geeky Gadgets Deals
Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
-and-Elon-Musk.jpeg%3Fwidth%3D1200%26height%3D800%26crop%3D1200%3A800&w=3840&q=100)
The Independent
12 minutes ago
- The Independent
Republicans call for an end to Trump-Musk feud: ‘I hope it doesn't distract us'
As the Republican Party anticipates potential fallout from Donald Trump's public dispute with Elon Musk, prominent lawmakers and conservative voices are calling for reconciliation, wary of the repercussions of a sustained conflict. The animosity between the two figures could pose challenges for the Republican agenda, particularly concerning tax and border spending legislation championed by Trump but criticised by Musk. Representative Dan Newhouse, a Republican from Washington, expressed hope that the disagreement would not impede progress on critical tasks. Speaking on the matter, Newhouse said: "I hope it doesn't distract us from getting the job done that we need to. I think that it will boil over and they'll mend fences." As of Friday afternoon, Musk had refrained from further engagement, focusing instead on promoting his various companies on social media. Senator Ted Cruz, a Texas Republican, voiced optimism for a resolution, telling Fox News that, "I hope that both of them come back together because when the two of them are working together, we'll get a lot more done for America than when they're at cross purposes". Sen. Mike Lee, a Republican from Utah, sounded almost pained on social media as Trump and Musk volleyed insults at each other, sharing a photo composite of the two men and writing, "But … I really like both of them.' 'Who else really wants @elonmusk and @realDonaldTrump to reconcile?' Lee posted, later adding: 'Repost if you agree that the world is a better place with the Trump-Musk bromance fully intact.' So far, the feud between Trump and Musk is probably best described as a moving target, with plenty of opportunities for escalation or detente. One person familiar with the president's thinking said Musk wants to speak with Trump, but that the president doesn't want to do it – or at least do it on Friday. The person requested anonymity to disclose private matters. In a series of conversations with television anchors Friday morning, Trump showed no interest in burying the hatchet. Asked on ABC News about reports of a potential call between him and Musk, the president responded: 'You mean the man who has lost his mind?' Trump added in the ABC interview that he was 'not particularly' interested in talking to Musk at the moment. Still, others remained hopeful that it all would blow over. 'I grew up playing hockey and there wasn't a single day that we played hockey or basketball or football or baseball, whatever we were playing, where we didn't fight. And then we'd fight, then we'd become friends again,' Hannity said on his show Thursday night. Acknowledging that it 'got personal very quick,' Hannity nonetheless added that the rift was 'just a major policy difference.' House Speaker Mike Johnson projected confidence that the dispute would not affect prospects for the tax and border bill. 'Members are not shaken at all,' the Louisiana Republican said. 'We're going to pass this legislation on our deadline.' He added that he hopes Musk and Trump reconcile, saying 'I believe in redemption' and 'it's good for the party and the country if all that's worked out.' But he also had something of a warning for the billionaire entrepreneur. 'I'll tell you what, do not doubt and do not second-guess and don't ever challenge the president of the United States, Donald Trump,' Johnson said. "He is the leader of the party. He's the most consequential political figure of this generation and probably the modern era.'
Geeky Gadgets
15 minutes ago
- Geeky Gadgets
Stop AI Hallucinations : Transform Your n8n Agent into a Precision Powerhouse
What if your AI agent could stop making things up? Imagine asking it for critical data or a precise task, only to receive a response riddled with inaccuracies or irrelevant details. These so-called 'hallucinations' are more than just a nuisance—they can derail workflows, undermine trust, and even lead to costly mistakes. But here's the good news: by fine-tuning your n8n AI agent settings, you can dramatically reduce these errors and unlock a level of performance that's both reliable and context-aware. From selecting the right chat model to configuring memory for seamless context retention, the right adjustments can transform your AI from unpredictable to indispensable. In this comprehensive guide, FuturMinds take you through the best practices and critical settings to optimize your n8n AI agents for accuracy and efficiency. Learn how to choose the perfect chat model for your needs, fine-tune parameters like sampling temperature and frequency penalties, and use tools like output parsers to ensure structured, reliable responses. Whether you're aiming for professional-grade results in technical workflows or simply want to minimize hallucinations in everyday tasks, this report will equip you with actionable insights to achieve your goals. Because when your AI agent performs at its best, so do you. n8n AI Agent Configuration Choosing the Right Chat Model The foundation of a reliable AI agent begins with selecting the most suitable chat model. Each model offers unique capabilities, and aligning your choice with your specific use case is crucial for optimal performance. Consider the following options: Advanced Reasoning: Models like Anthropic or OpenAI GPT-4 are designed for complex problem-solving and excel in tasks requiring nuanced understanding. Models like Anthropic or OpenAI GPT-4 are designed for complex problem-solving and excel in tasks requiring nuanced understanding. Cost Efficiency: Lightweight models such as Mistral are ideal for applications where budget constraints are a priority without compromising too much on functionality. Lightweight models such as Mistral are ideal for applications where budget constraints are a priority without compromising too much on functionality. Privacy Needs: Self-hosted options like Olama provide enhanced data control, making them suitable for sensitive or proprietary information. Self-hosted options like Olama provide enhanced data control, making them suitable for sensitive or proprietary information. Multimodal Tasks: For tasks involving both text and images, models like Google Gemini or OpenAI's multimodal models are highly effective. To improve efficiency, consider implementing dynamic model selection. This approach routes tasks to the most appropriate model based on the complexity and requirements of the task, making sure both cost-effectiveness and performance. Fine-Tuning AI Agent Parameters Fine-tuning parameters is a critical step in shaping your AI agent's behavior and output. Adjusting these settings can significantly enhance the agent's performance and reliability: Frequency Penalty: Increase this value to discourage repetitive responses, making sure more diverse and meaningful outputs. Increase this value to discourage repetitive responses, making sure more diverse and meaningful outputs. Sampling Temperature: Use lower values (e.g., 0.2) for factual and precise outputs, while higher values (e.g., 0.8) encourage creative and exploratory responses. Use lower values (e.g., 0.2) for factual and precise outputs, while higher values (e.g., 0.8) encourage creative and exploratory responses. Top P: Control the diversity of responses by limiting the probability distribution, which helps in generating more focused outputs. Control the diversity of responses by limiting the probability distribution, which helps in generating more focused outputs. Maximum Tokens: Set appropriate limits to balance response length and token usage, avoiding unnecessarily long or truncated outputs. For structured outputs such as JSON, combining a low sampling temperature with a well-defined system prompt ensures accuracy and consistency. This approach is particularly useful for technical applications requiring predictable and machine-readable results. Best n8n AI Agent Settings Explained Watch this video on YouTube. Stay informed about the latest in n8n AI agent configuration by exploring our other resources and articles. Configuring Memory for Context Retention Memory configuration plays a vital role in maintaining context during multi-turn conversations. Proper memory management ensures that responses remain coherent and relevant throughout the interaction. Key recommendations include: Context Window Length: Adjust this setting to retain essential information while staying within token limits, making sure the agent can reference prior exchanges effectively. Adjust this setting to retain essential information while staying within token limits, making sure the agent can reference prior exchanges effectively. Robust Memory Nodes: For production environments, use reliable options like PostgreSQL chat memory via Supabase to handle extended interactions without risking data loss or crashes. Avoid using simple memory nodes in production, as they may not provide the stability and scalability required for complex or long-running conversations. Enhancing Functionality with Tool Integration Integrating tools expands your AI agent's capabilities by allowing it to perform specific actions via APIs. This functionality is particularly useful for automating tasks and improving efficiency. Examples include: Email Management: Integrate Gmail to send, organize, and manage emails directly through the AI agent. Integrate Gmail to send, organize, and manage emails directly through the AI agent. Custom APIs: Add domain-specific tools for specialized tasks, such as retrieving financial data, generating reports, or managing inventory. To minimize hallucinations, clearly define the parameters and scope of each tool. This ensures the agent understands its limitations and uses the tools appropriately within the defined context. Optimizing System Prompts A well-crafted system prompt is essential for defining the AI agent's role, goals, and behavior. Effective prompts should include the following elements: Domain Knowledge: Specify the agent's expertise and focus areas to ensure it provides relevant and accurate responses. Specify the agent's expertise and focus areas to ensure it provides relevant and accurate responses. Formatting Rules: Provide clear instructions for structured outputs, such as JSON, tables, or bullet points, to maintain consistency. Provide clear instructions for structured outputs, such as JSON, tables, or bullet points, to maintain consistency. Safety Instructions: Include guidelines to prevent inappropriate, harmful, or biased responses, making sure ethical and responsible AI usage. Using templates for system prompts can streamline the configuration process and reduce errors, especially when deploying multiple agents across different use cases. Using Output Parsers Output parsers are invaluable for enforcing structured and predictable responses. They are particularly useful in applications requiring machine-readable outputs, such as data pipelines and automated workflows. Common types include: Structured Output Parser: Ensures responses adhere to predefined formats, such as JSON or XML, for seamless integration with other systems. Ensures responses adhere to predefined formats, such as JSON or XML, for seamless integration with other systems. Item List Output Parser: Generates clear and organized lists with specified separators, improving readability and usability. Generates clear and organized lists with specified separators, improving readability and usability. Autofixing Output Parser: Automatically corrects improperly formatted outputs, reducing the need for manual intervention. Incorporating these tools enhances the reliability and usability of your AI agent, particularly in technical and data-driven environments. Additional Settings for Enhanced Performance Fine-tuning additional settings can further improve your AI agent's reliability and adaptability. Consider the following adjustments: Iteration Limits: Set a maximum number of iterations for tool usage loops to prevent infinite cycles and optimize resource usage. Set a maximum number of iterations for tool usage loops to prevent infinite cycles and optimize resource usage. Intermediate Steps: Enable this feature to debug and audit the agent's decision-making process, providing greater transparency and control. Enable this feature to debug and audit the agent's decision-making process, providing greater transparency and control. Multimodal Configuration: Ensure the agent can handle binary image inputs for tasks involving visual data, expanding its range of applications. These settings provide greater control over the agent's behavior, making it more versatile and effective in handling diverse scenarios. Best Practices for Continuous Improvement Building and maintaining a high-performing AI agent requires ongoing monitoring, testing, and refinement. Follow these best practices to ensure optimal performance: Regularly review and adjust settings to enhance response quality, reduce token usage, and address emerging requirements. Test the agent in real-world scenarios to identify potential issues and implement necessary improvements. Align tools, configurations, and prompts with your specific use case and objectives to maximize the agent's utility and effectiveness. Consistent evaluation and optimization are essential for making sure your AI agent remains reliable, efficient, and aligned with your goals. Media Credit: FuturMinds Filed Under: AI, Guides Latest Geeky Gadgets Deals Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
Reuters
23 minutes ago
- Reuters
Foreign exposure to US assets may be lower than feared
ORLANDO, Florida, June 3 (Reuters) - It is widely believed that investors around the world have a disproportionately high exposure to U.S. assets, particularly stocks, an imbalance that could roil U.S. markets if corrected. But what if these fears are overblown? Several eye-popping statistics suggest that America's weight in world financial markets is even greater than its outsized economic might. Most strikingly, the U.S. net international investment position (NIIP), or foreign investors' holdings of U.S. assets less U.S. investors' holdings of overseas assets, at the end of 2024 was $26 trillion. That's nearly 24% of global GDP, up from 16% only two years earlier, a surge driven by foreigners' insatiable appetite for U.S. equities, mainly "Big Tech". Demand was so hot that, by some measures, the value of U.S.-listed stocks at the turn of the year represented 74% of total global market cap. That share was 60% six years ago, and less than half in 2011. But the attractiveness of dollar-denominated assets is now being questioned, as the often erratic policies of U.S. President Donald Trump have upset longstanding economic and geopolitical norms, making governments and investors question whether Washington is still a reliable partner on the global stage. The concern is that this eroding confidence triggers a reversal of the massive flows into Wall Street seen in recent years that has damaging spillover effects. Such a correction may not require outright selling. Given the scale of the flows involved, just less buying among foreign investors could be enough to cast a shadow over the world's most important stock market. And the running assumption is foreign investors don't have the capacity or willingness to increase their exposure to U.S. assets, creating a significant long-term downside risk for Wall Street, Treasuries and the dollar. "A structural shift is underway: the slow erosion of US economic dominance," analysts at Deutsche Bank wrote on Monday. But looked at another way, foreign exposure to U.S. assets may not be as high as initially meets the eye. That's the view of analysts at JP Morgan, who measure portfolio investment in U.S. bonds and equities as a share of countries' total household sector financial assets. They use a broad definition for a country's "household" sector, covering investments by institutions like insurance companies and pension funds that are ultimately made on behalf of households. Using a broad range of data, from central banks, U.S. Treasury and OECD household financial asset flows, they measure the ratio of U.S. equity and bond holdings relative to household financial assets in each country. They find that "relative to the total financial assets of households in the rest of the world, the allocations to U.S. assets typically stand at around 10-20%." As a result, they are "skeptical of the idea that foreign investors hold too much of U.S. assets." Given that U.S. equities account for more than 70% of the MSCI global market cap and dollar-denominated bonds represent around 50% of global bond indices, according to JP Morgan estimates, the 10-20% exposure of foreign investors to U.S. assets does appear surprisingly low. And the 10-20% figure would be even lower were it not for the outsized U.S. equity holdings at the Swiss National Bank and Norway's sovereign wealth fund. On the bond side, foreigners' footprint in the U.S. Treasury market is shrinking. Data shows that they owned 31% of the $28.55 trillion outstanding Treasury debt at the end of last year. That share has been declining steadily since the Global Financial Crisis. In 2008, the figure was approaching 60%. Overseas investors' share of the T-bill market has shrunk even more. In December, it was under 20%, near its lowest level on record and sharply down from 50% a decade before. Nikolaos Panigirtzoglou and his team at JP Morgan aren't arguing investors will or should ramp up their purchases of U.S. assets. And in cases where allocations are high - such as the Taiwanese exposure to U.S. bonds or Canadians' holdings of U.S. stocks - diversification would hardly be a surprise. But there is "little indication" of broad-based selling of U.S. assets by foreign investors so far this year, they note. And if that selling does materialize, it may be far lighter than many expect. (The opinions expressed here are those of the author, a columnist for Reuters)
