How To Use GPT-4 Yourself With Ted Lappas

If you’re already in the middle of using ChatGPT, you may be prompted to make the switch to GPT-4. Once you’re a paying customer, your access to the new model via ChatGPT will be immediate. Another useful process is known as in-painting, where the system ingests an image and edits it. For instance it could replace a cocker spaniel with a Labrador, and adapt the background to make the new image seamless.

But OpenAI likely sees it as a steppingstone toward something far more powerful. In one informal test, OpenAI prompted GPT-4.5 and two other models, GPT-4o and o3-mini, to create a unicorn in SVG, a format for displaying graphics based on mathematical formulas and code. GPT-4.5 was the only AI model to create anything resembling a unicorn.

How does Deep Search work?

Indeed, OpenAI says that GPT-4.5’s increased size has given it “a deeper world knowledge” and “higher emotional intelligence.” However, there are signs that the gains from scaling up data and computing are beginning to level off. On several AI benchmarks, GPT-4.5 comes under newer AI “reasoning” models from Chinese AI startup DeepSeek, Anthropic, and OpenAI itself. As a content marketing professional, I’ve been following OpenAI’s GPT series of large language models (LLMs) for a long time. However, it wasn’t until ChatGPT was released last autumn that the general public caught on to the brilliance of this technology that is—pardon the buzzword—truly disruptive.

How ChatGPT actually works (and why it’s been so game-changing)

He says it makes him more like a conductor of an orchestra than a writer, and it saves him five or six hours on each issue of the journal. The last few episodes of the London Futurists Podcast have explored what GPT (generative pre-trained transformer) technology is and how it works, and also the call for a pause in the development of advanced AI. In the latest episode, Ted Lappas, a data scientist and academic, helps us to understand what GPT technology can do for each of us individually. Using ChatGPT to analyze our code and find errors where we can’t ourselves has sped up our debugging process hugely—sometimes by entire hours that we would’ve spent digging around forums or contacting colleagues for solutions.

I haven’t had a chance to test that hands-on, but I’ll share with you some of OpenAI’s test results and some anecdotal reports by API users who moved from GPT-4o to GPT-4.1. For chat users, I’ve found it’s just easier to recommend you think of each like a car model name, each with its own characteristics. An easy answer is that GPT-4.1 is the new, better version of GPT that exceeds the performance of the more mainstream GPT-4o.

• This reportedly happens a lot less with this model, but it’s not immune, raising concerns over its use in accuracy-sensitive environments.
• The easiest way to understand this behavior is assuming that if your search contains a “why,” Deep Search will add the “how,” “when,” and “where” part to it in the expanded form.
• In a nutshell, if AI was ever destined to reimagine the web search experience and make it more rewarding, Deep Search is the answer.
• Box CEO Aaron Levie said on X that his company used GPT-4.5 to help extract structured data and metadata from complex enterprise content.
• In practice, there are big differences in terms of how much compute power is used and how big a problem they can solve, but those nuances are mostly of concern to programmers who are paying OpenAI based on their usage.
• Tapping on it opens the Copilot with Bing Chat window, where you can enter a query; it will pull answers from the web in paragraph form, with source citations in tow.

OpenAI brings its powerful GPT-4.1 models to ChatGPT with improved coding tasks and follow-up instructions.

When a user types in a single-sentence search query, the AI model exploits its generative capabilities and expands the search query by adding multiple contextual expansions to it, as described above. The easiest way to understand this behavior is assuming that if your search contains a “why,” Deep Search will add the “how,” “when,” and “where” part to it in the expanded form. On OpenAI’s SimpleQA benchmark, which tests AI models on straightforward, factual questions, GPT-4.5 outperforms GPT-4o and OpenAI’s reasoning models, o1 and o3-mini, in terms of accuracy. According to OpenAI, GPT-4.5 hallucinates less frequently than most models, which in theory means it should be less likely to make stuff up.

Here’s how I’m going to integrate GPT technology into my life and how I hope you can, too.

It can understand humor

• Now, in just about a month, the new generation AI models have started to roll out to ChatGPT.
• But the bot saves me an hour or so in the production of each chapter, and it also makes the process more fun.
• At the time of writing, GPT-4 is trained on data that was collected up until August 2022, so it has no knowledge beyond that date.
• Both Snake and Pong were recreated from scratch, despite the users having next to no experience with programming.
• I remember being a part of a hackathon trying to find concrete prompts where GPT4 outperformed 3.5.

OpenAI also claims that GPT-4.5 is qualitatively superior to other models in areas that benchmarks don’t capture well, like the ability to understand human intent. GPT-4.5 responds in a warmer and more natural tone, OpenAI says, and performs well on creative tasks such as writing and design. OpenAI announced on Thursday it is launching GPT-4.5, the much-anticipated AI model code-named Orion.

It can write beautifully, is very creative, and is occasionally oddly lazy on complex projects.Feels like Claude 3.7 while Claude 3.7 feels like GPT-4.5. Small models have been gaining traction in the industry for a while now as a faster and more cost-efficient alternative to larger, foundation models. OpenAI released its first small model, o3 mini, in January, just weeks after Chinese startup Butterfly Effect debuted DeepSeek’s R1, which shocked Silicon Valley — and the markets — with its affordable pricing. However, it also raised copyright questions as critics argued that OpenAI is unfairly profiting off artists’ content.

GPT-4.5

It feels a little creepy at times, but ChatGPT can now be used for much more personalized tasks. OpenAI pitches this as a way to improve its scheduling feature to use it as a personal assistant, or to help you continue longer chats over extended periods of time. But it’s also quite fun to see what ChatGPT can tell you by trawling throughh all your chatlogs. Whether you’re building a GPT 3.5 chatbot using the free tier, or a GPT-4 model as part of a subscription, the process for creating the chatbot is the same.

That’s roughly the equivalent of Ford coming out with a new engine but selling it only to mechanics to put in custom cars. We give you the inside scoop on what companies are doing with generative AI, from regulatory shifts to practical deployments, so you can share insights for maximum ROI. Upgrade your lifestyleDigital Trends helps readers keep tabs on the fast-paced world of tech with all the latest news, fun product reviews, insightful editorials, and one-of-a-kind sneak peeks. Once it has gathered the relevant search results, it does topic-matching to deliver the most apt answers. But while doing so, it also takes into consideration factors such as trust and authority in the source, the freshness of the source material, and whether it provides the appropriate depth and detail. In other words, there’s a good chance you’re going to be interacting with GPT-4 soon, whether you like it or not.