Posts tagged with "OpenAI"

Building Tools with GPT-5→

Yesterday, Parker Ortolani wrote about several vibe coding projects he’s been working on and his experience with GPT-5:

The good news is that GPT-5 is simply amazing. Not only does it design beautiful user interfaces on its own without even needing guidance, it has also been infinitely more reliable. I couldn’t even count the number of times I have needed to work with the older models to troubleshoot errors that they created themselves. Thus far, GPT-5 has not caused a single build error in Xcode.

I’ve had a similar initial experience. Leading up to the release of GPT-5, I used Claude Opus 4 and 4.1 to create a Python script that queries the Amazon Product Advertising API to check whether there are any good deals on a long list of products. I got it working, but it typically returned a list of 200-300 deals sorted by discount percentage.

Though those results were fine, a percentage discount only roughly correlates to whether something is a good deal. What I wanted was to rank the deals by assigning different weights to several factors and coming up with a composite score for each. Having reached my token limits with Claude, I went to GPT-o3 for help, and it failed, scrambling my script. A couple of days later, GPT-5 launched, so I gave that a try, and it got the script right on the very first try. Now, my script spits out a spreadsheet sorted by rank, making spotting the best deals a little easier than before.

In the days since, I’ve used GPT-5 to set up a synced Python environment across two Macs and begun the process of creating a series of Zapier automations to simplify other administrative tasks. These tasks are all very specific to MacStories and the work I do, so I’ve stuck with scripting them instead of building standalone apps. However, it’s great to hear about Ortolani’s experiences with creating interfaces for native and web apps. It opens up the possibility of creating tools for the rest of the MacStories team that would be easier to install and maintain than walking people through what I’ve done in Terminal.

This statement from Ortolani also resonated with me:

As much as I can understand what code is when I’m looking at it, I just can’t write it. Vibe coding has opened up a whole new world for me. I’ve spent more than a decade designing static concepts, but now I can make those concepts actually work. It changes everything for someone like me.

I can’t decide whether this is like being able to read a foreign language without knowing how to speak it or the other way around, but I completely understand where Ortolani is coming from. It’s helped me a lot to have a basic understanding of how code works, how apps are built, and – as Ortolani mentions – how to write a good prompt for the LLM you’re using.

What’s remarkable to me is that those few ingredients combined with GPT-5 have gone such a long way to eliminate the upfront time I need to get projects like these off the ground. Instead of spending days on research without knowing whether I could accomplish what I set out to do, I’ve been able to just get started and, like Ortolani, iterate quickly, wasting little time if I reach a dead end and, best of all, shortening the time until I have a result that makes my life a little easier.

Federico and I have said many times that LLMs are another form of automation and automation is just another form of coding. GPT-5 and Claude Opus 4.1 are rapidly blurring the lines between both, making automation and coding more accessible than ever.

Permalink

OpenAI to Buy Jony Ive’s Stealth Startup for $6.5 Billion→

Jony Ive’s stealth AI company known as io is being acquired by OpenAI for $6.5 billion in a deal that is expected to close this summer subject to regulatory approvals. According to reporting by Mark Gurman and Shirin Ghaffary of Bloomberg:

The purchase — the largest in OpenAI’s history — will provide the company with a dedicated unit for developing AI-powered devices. Acquiring the secretive startup, named io, also will secure the services of Ive and other former Apple designers who were behind iconic products such as the iPhone.

The partnership builds on a 23% stake in io that OpenAI purchased at the end of last year and comes with what Bloomberg describes as 55 hardware engineers, software developers, and manufacturing experts, plus a cast of accomplished designers.

Ive had this to say about the purportedly novel products he and OpenAI CEO Sam Altman are planning:

“People have an appetite for something new, which is a reflection on a sort of an unease with where we currently are,” Ive said, referring to products available today. Ive and Altman’s first devices are slated to debut in 2026.

Bloomberg also notes that Ive and his team of designers will be taking over all design at OpenAI, including software design like ChatGPT.

For now, the products OpenAI is working on remain a mystery, but given the purchase price and io’s willingness to take its first steps into the spotlight, I expect we’ll be hearing more about this historic collaboration in the months to come.

Permalink

Sycophancy in GPT-4o→

OpenAI found itself in the middle of another controversy earlier this week, only this time it wasn’t about publishers or regulation, but about its core product – ChatGPT. Specifically, after rolling out an update to the default 4o model with improved personality, users started noticing that ChatGPT was adopting highly sycophantic behavior: it weirdly agreed with users on all kinds of prompts, even about topics that would typically warrant some justified pushback from a digital assistant. (Simon Willison and Ethan Mollick have a good roundup of the examples as well as the change in the system prompt that may have caused this.) OpenAI had to roll back the update and explain what happened on the company’s blog:

We have rolled back last week’s GPT‑4o update in ChatGPT so people are now using an earlier version with more balanced behavior. The update we removed was overly flattering or agreeable—often described as sycophantic.

We are actively testing new fixes to address the issue. We’re revising how we collect and incorporate feedback to heavily weight long-term user satisfaction and we’re introducing more personalization features, giving users greater control over how ChatGPT behaves.

And:

We also believe users should have more control over how ChatGPT behaves and, to the extent that it is safe and feasible, make adjustments if they don’t agree with the default behavior.

Today, users can give the model specific instructions to shape its behavior with features like custom instructions. We’re also building new, easier ways for users to do this. For example, users will be able to give real-time feedback to directly influence their interactions and choose from multiple default personalities.

“Easier ways” for users to adjust ChatGPT’s behavior sound to me like a user-friendly toggle or slider to adjust ChatGPT’s personality (Grok has something similar, albeit unhinged), which I think would be a reasonable addition to the product. I’ve long argued that Siri should come with an adjustable personality similar to CARROT Weather, which lets you tweak whether you want the app to be “evil” or “professional” with a slider. I increasingly feel like that sort of option would make a lot of sense for modern LLMs, too.

Permalink

A Peek Into LookUp’s Word of the Day Art and Why It Could Never Be AI-Generated

Yesterday, Vidit Bhargava, developer of the award-winning dictionary app LookUp, wrote on his blog about the way he hand-makes each piece of artwork that accompanies the app’s Word of the Day. While revealing that he has employed this practice every day for an astonishing 10 years, Vidit talked about how each image is made from scratch as an illustration or using photography that he shoots specifically for the design:

Each Word of the Day has been illustrated with care, crafting digital illustrations, picking the right typography that conveys the right emotion.

Some words contain images, these images are painstakingly shot, edited and crafted into a Word of the Day graphic by me.

I’ve noticed before that each Word of the Day image in LookUp seemed unique, but I assumed Vidit was using stock imagery and illustrations as a starting point each time. The revelation that he is creating almost all of these from scratch every single day was incredible and gave me a whole new level of respect for the developer.

The idea of AI-generated art (specifically art that is wholly generated from scratch by LLMs) is something that really sticks in my throat – never more so than with the recent rip-off of the beautiful, hand-drawn Studio Ghibli films by OpenAI. Conversely, Vidit’s work shows passion and originality.

To quote Vidit, “Real art takes time, effort and perseverance. The process is what makes it valuable.”

You can read the full blog post here.

DeepSeek Tops the App Store Charts and Sends AI Stocks on a Wild Ride

DeepSeek's newfound popularity has made it impossible to log in as of the publication of this story.

DeepSeek’s newfound popularity has made it impossible to log in as of the publication of this story.

And just like that, ChatGPT has been dethroned from its perch at the top of the App Store’s free app list, replaced by DeepSeek, another AI app. What’s interesting is that DeepSeek, which was developed by a Chinese startup, was reportedly created at a fraction of the cost of ChatGPT and other large language models developed in the US, which has tech stocks in turmoil.

Last week, DeepSeek revealed its latest LLM, which matches or outperforms OpenAI’s o1 model in some tests. That’s nothing new. AI companies have been one-upping each other for months. What’s different is that DeepSeek was reportedly built with a fraction of the hardware and at a fraction of the cost of OpenAI’s o1 and models like Anthropic’s Claude.

DeepSeek is also open source, potentially undermining the financial viability of U.S. and other for-profit companies that have spent hundreds of millions of dollars developing models that require a paid subscription. And, because it’s free, DeepSeek rocketed to the top of the App Store’s free app list, passing OpenAI’s ChatGPT, which has been at or near the top of the list for months.

That has caused a stir in Silicon Valley. As VentureBeat’s Carl Franzen puts it:

The open-source availability of DeepSeek-R1, its high performance, and the fact that it seemingly “came out of nowhere” to challenge the former leader of generative AI, has sent shockwaves throughout Silicon Valley and far beyond, based on my conversations with and readings of various engineers, thinkers and leaders. If not “everyone” is freaking out about it as my hyperbolic headline suggests, it’s certainly the talk of the town in tech and business circles.

Now, as DeepSeek is starting to look like the real deal, the stock market is causing competitors’ stocks to drop, including NVIDIA’s, which, according to the Financial Times, fell 13% at the opening of the New York Stock Exchange.

If there’s one thing that has been a truism of the AI industry over the past couple of years, it’s that it moves very fast. Today’s leaders are tomorrow’s laggards. Will DeepSeek dethrone the U.S. AI companies? It’s far too early to know, but it certainly is beginning to look like there’s a new horse in the race.

Audio Hijack Gains Beta Audio Transcription Feature

I’ve been playing around a lot with OpenAI’s Whisper speech-to-text engine this year. Whisper isn’t perfect, but it does a remarkably good job, substantially lowering the effort and cost of generating transcripts.

There are dedicated apps to transcribe using Whisper like MacWhisper by Jordi Brun and Transcriptionist from the makers of Ferrite, both of which I’ve tried. However, the most promising option so far is a new Transcribe block released today as part of Audio Hijack by Rogue Amoeba.

The new block is a beta feature that Rogue Amoeba’s Paul Kafasis says the company will continue to refine. It’s using the same underlying Whisper technology as other apps, but by reducing transcription to part of your existing recording flow, it’s possible to transcribe on the fly as you record and identify speakers whose audio is coming from separate channels.

We weren’t recording any shows today, so to test the new feature, I copied our MacStories Unwind recording session and used the Zoom audio settings as a stand-in for Federico. I spoke into my microphone, which was one source, and used the piano music from Zoom’s settings as the other source. Audio Hijack recorded both and started transcribing the audio as I was still recording. Here are the results:

This was a very limited test. It remains to be seen how the app does with a longer recording session, but the ease with which I set this up has me excited. By renaming the sources fed into the Transcribe block, I was able to create a real-time transcript complete with timestamps and our names.

Still, as impressive as the results are, I don’t publish what I record in Audio Hijack. It still needs to be edited, at which point the transcript created with this session would diverge from the released audio. Nonetheless, for a newly released beta feature, I’m impressed and looking forward to seeing where Rogue Amoeba takes this.

Introducing S-GPT, A Shortcut to Connect OpenAI’s ChatGPT with Native Features of your iPhone, iPad, and Mac

S-GPT for Shortcuts.

S-GPT for Shortcuts.

It’s the inaugural week of the second annual edition of Automation April, and to celebrate the occasion, I’ve been working on something special: today, I’m introducing S-GPT, an advanced conversational shortcut for ChatGPT that bridges OpenAI’s assistant to native system features of iOS, iPadOS, macOS, and watchOS.

S-GPT (which stands for Shortcuts-GPT) is free to use for everyone, but it requires an OpenAI account with an associated pay-as-you-go billing plan since it takes advantage of OpenAI’s developer API, which has a cost. S-GPT was built with the latest ChatGPT API, and it can be used both with the existing ChatGPT 3.5 model or – if you have access to it – the ChatGPT 4 API.

While the shortcut is free for MacStories readers, I will be publishing a detailed, in-depth Automation Academy class soon for Club MacStories Plus or Premier members to explain the techniques and strategies I used to build this shortcut. I genuinely think that S-GPT is, from a technical perspective, my best and most advanced work to date; I hope my Academy class will help others learn some useful tips for Shortcuts and, in return, make even better automations for our contest.

With that said, let’s look at what S-GPT is and what you can do with it.

Read more