I've been testing ChatGPT-5 — and these 3 features are absolutely brilliant
Despite some early GPT-5 issues, the improvements here go beyond just better conversations. From customizing your chat experience to connecting directly with your Gmail and Google Calendar, these are practical tools that can streamline how you manage information and tasks. Here are the three standout features that make GPT-5 worth the upgrade, and exactly how to start using them today.
ChatGPT-5 adapts its approach based on the task. It can give quick replies for straightforward requests or slow down for more complex ones, without the user needing to change any settings.
It handles far longer conversations and documents than earlier versions, and it can work with images, charts, and other visuals alongside text.
Its tone and personality can be adjusted, and it responds more naturally to the way a person writes. It also decides on its own when to search the web or create an image. These changes make it a more flexible and capable assistant than previous versions.
While there are plenty of changes in ChatGPT-5, these three new features have stood out to me the most.
One of GPT-5's most impressive improvements is preset personalities that maintain their style throughout entire conversations. Previous versions would often revert to default responses after a few exchanges, but ChatGPT-5's improved "steerability" means these personality traits persist.
You can choose from options like Cynic, Robot and Listener, and choose a personality depending on what works best for your task. To set up personalities, navigate to Settings, Personalization, Custom instructions, then select your preferred preset from the available options.
The ChatGPT personality you choose affects tone, response length, and even how the AI approaches problem-solving, making interactions feel more natural and suited to your specific needs.
For Pro users ChatGPT-5 can now integrate directly with Gmail and Google Calendar, turning it into a genuine productivity assistant. Plus, Team and Enterprise users will gain access at a later date.
The AI can check your schedule to find free time, suggest meeting slots, and even help draft responses to emails you've been putting off. To enable this integration, go to Settings, Connectors and follow the on-screen instructions to link your Gmail and Google Calendar accounts.
This integration keeps you organized without having to switch between multiple apps and tabs. Once connected, you can ask ChatGPT to do things like "Remind me what meetings I have tomorrow?", or "Help me respond to that email from Joe Smith about the project deadline."
ChatGPT-5 finally lets you change the color scheme of your chat interface, moving beyond the standard design everyone's been stuck with. While this might seem like a minor cosmetic update, it actually makes a bigger difference than you'd expect.
To change your chat colors, click your profile icon on the bottom-left, Settings and the "General" section, where you'll find color customization options. You can choose from several preset colors/
The color changes apply immediately to your chat interface, making it feel more like your own personalized workspace rather than a generic AI tool. This small touch helps reduce the clinical feeling you sometimes get when interacting with AI.
Follow Tom's Guide on Google News to get our up-to-date news, how-tos, and reviews in your feeds. Make sure to click the Follow button.
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
33 minutes ago
- Yahoo
Elon Musk broadens his long-running feud with OpenAI's Sam Altman by bringing in a third party: Apple
Elon Musk's long-standing battle with OpenAI has a new participant: Tuesday, Apple found itself the latest target of Elon Musk's legal threats when the xAI CEO accused the tech giant of using unfair means to promote OpenAI's ChatGPT over his company's rival Grok chatbot in the App Store. Musk called it an 'unequivocal antitrust violation' and threatened to take legal action. OpenAI CEO Sam Altman, who is part of an ongoing feud with the billionaire, quickly weighed in on the dispute, calling Musk's accusation a 'remarkable claim.' He, in turn, accused Musk of manipulating his own platform, X, 'to benefit himself and his own companies and harm his competitors and people he doesn't like.' Apple has denied Musk's claims, saying in a statement that the App Store 'is designed to be fair and free of bias.' 'We feature thousands of apps through charts, algorithmic recommendations, and curated lists selected by experts using objective criteria,' a spokesperson said in a statement shared with news outlets. 'Our goal is to offer safe discovery for users and valuable opportunities for developers, collaborating with many to increase app visibility in rapidly evolving categories.' X users, and Musk's own Grok chatbot, were quick to point out that Musk's claim was undermined by apps like DeepSeek and Perplexity having previously taken the top slot on Apple's App Store. The issue may have more to do with Apple's standing deal with OpenAI's ChatGPT. Under a mid-2024 deal, ChatGPT is built into Siri and system-wide writing tools on an opt-in basis. Siri asks for permission before sending queries; no OpenAI account is required; and Apple has said it plans to support additional AI providers over time. Even so, the integration gives ChatGPT a prominent, first-party placement on hundreds of millions of Apple devices, potentially making it harder for rivals like Musk's xAI to win users' attention. With Google weaving its Gemini AI into Android, the mobile AI market could increasingly be shaped by default integrations, which could make it much harder for rivals like xAI to compete. The OpenAI and Apple deal appeared to get under the billionaire's skin when it was announced, with Musk taking to X to complain: 'It's patently absurd that Apple isn't smart enough to make their own AI, yet is somehow capable of ensuring that OpenAI will protect your security & privacy!' Musk went on to threaten to bar all Apple devices from his companies if OpenAI technology was integrated into iOS operating systems. Apple's antitrust issues Apple is currently at the center of several other antitrust battles. Apple's App Store is one of the few key platforms for app distribution. Whoever gets visibility there is effectively handed a huge share of new users, which has been a point of contention for some of its competitors. In the U.S., Apple's App Store practices have been under scrutiny since 2020 when the company was sued by Epic Games over the removal of Fortnite from the App Store for bypassing its payment system to avoid the 30% commission. A federal appeals court recently refused to pause an order from its long-running battle with Epic Games that forces Apple to allow developers to direct users to outside payment options. Last year, the Justice Department filed a landmark antitrust lawsuit accusing Apple of monopolizing the smartphone market, alleging that its App Store policies block new developers and stifle innovation. Apple has denied the allegations, saying that its practices foster innovation and consumer choice. In June, the U.S. District Court for the District of New Jersey denied Apple's motion to dismiss the lawsuit. In a separate case brought against Google by the Justice Department, Apple's $15 billion to $20 billion a year deal with the search giant could also be at stake after a federal judge declared in August last year that Google unlawfully maintained a monopoly in internet search, partly through exclusive agreements with companies like Apple. The deal, which made Google the default search engine on its devices, could be disrupted by the remedies currently being weighed by a judge, with JPMorgan analysts warning that a worst-case ruling could cost Apple about $12.5 billion annually. This story was originally featured on Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
The Verge
5 hours ago
- The Verge
The head of ChatGPT was 'surprised' by how much people were attached to GPT-4o.
All of the updates about OpenAI See all Stories Posted Aug 14, 2025 at 11:11 PM UTC Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates. Richard Lawler Posts from this author will be added to your daily email digest and your homepage feed. See All by Richard Lawler Posts from this topic will be added to your daily email digest and your homepage feed. See All AI Posts from this topic will be added to your daily email digest and your homepage feed. See All News Posts from this topic will be added to your daily email digest and your homepage feed. See All OpenAI
Fast Company
5 hours ago
- Fast Company
From experimentation to transforming customer value
Since ChatGPT was released nearly three years ago, individuals and companies have experimented with reactive AI, composing AI prompts to create articles, tables, translations, to-do lists, and chatbots to resolve questions. While these tasks offer practical value, especially boosting efficiency, the next leap isn't just technical. Agentic AI systems can enable organizations to deploy autonomous service agents capable of managing entire organizational processes end to end. The value of agentic AI lies in collaboration, not replacement, where humans and machines each play to their strengths. When workflows combine human judgment with machine precision, organizations can streamline tasks, innovate personalization and insights, sharpen decisions, scale, and measure outcomes that inform ongoing process upgrades. Unlike reactive AI, agentic systems function as digital colleagues, taking initiative, pursuing goals, having memory and context, using tools to learn from outcomes, and adapting in real time. This shift unlocks incremental gains and breakthrough innovation in customer and user experience through reimagined workflows for operational excellence. The catch? Redefining how an organization operates to deliver differentiating value requires careful human orchestration. While agentic AI acts autonomously, it depends on human or enterprise oversight to anchor purpose, set guardrails, and ensure alignment. Effectively implementing agentic AI prioritizes the role of human employees in value creation to a higher level, ensuring transparency, ethical standards, and responsible strategic oversight at every level. Enable seamless integration: The Model Context Protocol To realize agentic AI's full potential, organizations need to connect AI agents to multiple tools and data sources without building custom integrations for each one. Enter the Model Context Protocol (MCP)—an open standard that replaces fragmented integrations with a single, universal protocol. Think of MCP as a USB-C port for AI agents. Just as USB-C standardized device connections, MCP standardizes how AI systems access databases, applications, and external services. No more writing separate code for each integration. For businesses, this means autonomous agents can seamlessly access customer databases, CRM systems, knowledge repositories, and execute actions across platforms—all through one standardized protocol. As the ecosystem matures, AI systems maintain context while moving between tools and datasets, creating a sustainable architecture. The result? Dramatically reduced technical complexity and agents with the contextual awareness to deliver transformative customer value. Change management for cross-functional process reengineering Implementing the transformative value of agentic AI requires organizational change management—redesigning organizational processes that efficiently yield quality outcomes. Not just a new tool, impactful agentic AI implementation requires an AI expert as a vital ongoing member of cross-functional mission-based teams focused on a specific process selected for re-engineering. AI experts should not be siloed in the technical function. They should be embedded with the functional process content and outcomes experts, learning from each other as they expand organizational expertise. As the number of reimagined process teams grows, so does the organizational expertise, extending gains achieved and staying ahead of a continuously evolving AI. All of this requires careful orchestration of data, strategy, and organizational readiness focused on the functions to which agentic AI is applied and a work culture that adapts to discover new opportunities. This is transformational enterprise change. It is not an event but a new way of working. The potential, however, is substantial. If your organization is still only implementing prompt engineering, you are lagging. Prioritize process re-engineering targets Another key factor is how to prioritize which re-engineered processes customers and users will value most by seeing how they use the product or service. In the early 1980s, then-NCR Corporation used observational research to identify the most time-consuming challenges their retail cash registers could automate. NCR collaboratively developed the Small Computer System Interface (SCSI) protocol and developed a SCSI computer chip that enabled scanning charges to replace hand entry. Similarly standing in their customers' shoes, Intuit engineers and product managers spur innovation by regularly engaging in ' follow-me-home ' with customers seeing how users apply their product features in their daily lives. This institutionalizes technical experts' insights into customer usage to feed innovative ideas for more transformation. Train for an AI world Companies recognizing employees' AI skill gaps are providing in-house or commercial training for workers. Higher ed institutions and their nonacademic competitors offer a variety of online courses. With AI continuously evolving, the next generation and their teachers also need training. The American Federation of Teachers (AFT), America's second largest teachers' union, is starting a training hub with $23 million in funding from Microsoft, OpenAI, and Anthropic to focus on training teachers to generate lesson plans with AI wisely, safely and ethically. AFT's Share My Lesson is now Beta testing an OpenAI-powered teaching assistant, TRYEdBrAIn, that can adapt lesson plans to change grade levels, translate into different languages and many other options. Beta testing is now underway to understand user experience. The Khan Academy is testing an AI-powered teacher assistant as a student tutor in various school districts. As digital transformation accelerates, leading organizations will see agentic AI not as a tool, but as a catalyst for new paradigms of teamwork, value creation, and enterprise agility.
