ZDNET’s key takeaways
- OpenAI’s new GPT-5 flagship failed half of my programming checks.
- Earlier OpenAI releases have had nearly good outcomes.
- Now that OpenAI has enabled fallbacks to different LLMs, there are alternatives.
So GPT-5 happened. It is out. It is launched. It is the discuss of the digital city. And it is bought some issues. I am not gonna bury the lede. GPT-5 has failed half of my programming tests. That is the worst that OpenAI’s flagship LLM has ever accomplished on my rigorously designed checks.
Additionally: The best AI for coding in 2025 (and what not to use)
Earlier than I get into the main points, let’s take a second to debate one different little characteristic that is additionally a bit wonky. Try the brand new Edit button on the highest of the code dumps it generates.
Clicking the Edit button takes you into a pleasant little code editor. Right here, I changed the Writer discipline, proper in ChatGPT’s outcomes.
That appeared good, but it surely finally proved futile. After I closed the editor, it requested me if I needed to avoid wasting. I did. Then this unhelpful message confirmed up.
I by no means did get again to my authentic session. I needed to submit my authentic immediate once more, and let GPT-5 do its work a second time.
However wait. There’s extra. Let’s dig into my take a look at outcomes…
1. Writing a WordPress plugin
This was my very first test of coding prowess for any AI. It is what gave me that first “the world is about to alter” feeling, and it was accomplished utilizing GPT-3.5.
Subsequent checks, utilizing the identical immediate however with completely different AI fashions, generated blended outcomes. Some AIs did nice, some did not. Some AIs, like these from Microsoft and Google, improved over time.
Additionally: How I test an AI chatbot’s coding ability – and you can, too
ChatGPT’s mannequin has been the gold normal for this take a look at because the very starting. That makes the outcomes of GPT-5 all that rather more curious.
So, look, the precise coding with GPT-5 was partially profitable. GPT-5 generated a single block of code, which I pasted right into a file and was in a position to run. It supplied the requisite UI.
After I pasted within the take a look at names, it dynamically up to date the road rely, though it described it as “Line to randomize” as a substitute of “Traces to randomize.”
However then, after I clicked Randomize, it did not. As a substitute, it redirected me to instruments.php. What?? ChatGPT has by no means had an issue with this take a look at, whether or not GPT-3.5, GPT-4, or GPT-4o. You imply to inform me that OpenAI’s much-anticipated GPT-5 is failing proper out of the gate? Ouch.
I then gave GPT-5 this immediate.
After I click on randomize, I am taken to http://testsite.native/wp-admin/instruments.php. I don’t get an inventory of randomized outcomes. Are you able to repair?
The outcome was a line to patch. I am not thrilled with that strategy as a result of it requires the consumer to dig by means of code and to make no errors changing a line.
So, I requested GPT-5 for a full plugin. It gave me the complete textual content of the plugin to repeat and paste. This time, it labored.
This time, it did randomize the strains. When it encountered duplicates, it separated them from one another, because it was instructed. Lastly.
Additionally: I found 5 AI content detectors that can correctly identify AI text 100% of the time
I am sorry, OpenAI. I’ve to fail you on this take a look at. You’d have handed if the one error was not utilizing the plural of “line” when applicable. However the truth that it gave me again a non-working plugin on the primary attempt is fail territory, even when the AI did ultimately make it work on the second attempt.
Irrespective of the way you spin it, this can be a step again.
2. Rewriting a string operate
This second take a look at is designed to rewrite a string operate to higher test for {dollars} and cents. The unique code that GPT-5 was requested to rewrite didn’t permit for cents (it solely checked for integers).
GPT-5 did positive with this take a look at. It did return a minimal outcome as a result of it did not do any error checking. It did not test for non-string enter, further whitespace, hundreds separators, or forex symbols.
However that is not what I requested for. I advised it to rewrite a operate, which itself didn’t have any error checking. GPT-5 did precisely what I requested with no embellishment. I am type of glad of that as a result of it does not know whether or not or not code previous to this routine already did that work.
GPT-5 handed this take a look at.
3. Discovering an annoying bug
This take a look at happened as a result of I used to be battling a less-than-obvious bug in my code. With out going into the weeds about how the WordPress framework works, the apparent reply isn’t the precise reply.
You want some pretty arcane data about how WordPress filters go their data. This take a look at has been a stumbling block for quite a lot of AI LLMs.
Additionally: Gen AI disillusionment looms, according to Gartner’s 2025 Hype Cycle report
GPT-5, nonetheless, like GPT-4 and GPT-4o earlier than it, did perceive the issue. It articulated a transparent resolution.
GPT-5 handed this take a look at.
4. Writing a script
This take a look at asks the AI to include a reasonably obscure Mac scripting device known as Keyboard Maestro, in addition to Apple’s scripting language AppleScript, and Chrome scripting habits.
It is actually a take a look at of the attain of the AI when it comes to data, its understanding of how net pages are constructed, and the flexibility to put in writing code throughout three interlinked environments.
Fairly just a few AIs have failed this take a look at, however the failure level is often a lack of expertise about Keyboard Maestro. GPT-3.5 did not learn about Keyboard Maestro. However ChatGPT has been passing this take a look at since GPT-4. Till now.
The place ought to we begin? Nicely, the excellent news is that GPT-5 dealt with the Keyboard Maestro a part of the issue simply positive. Nevertheless it bought the coding so fallacious that it even doubled down on its lack of awareness of how case works in AppleScript.
It truly invented a property. That is a type of instances the place an AI confidently presents a solution that’s fully fallacious.
Additionally: ChatGPT comes with personality presets now – and other upgrades you might have missed
AppleScript is natively case-insensitive. If you’d like AppleScript to concentrate to case, it is advisable to use a “contemplating case” block. So, this occurred.
The rationale the error message referred to the title of one in all my articles is as a result of that was the entrance window in Chrome. This operate checks the entrance window and does stuff based mostly on the title.
However misunderstanding how case works wasn’t the one AppleScript error GPT-5 generated. It additionally referenced a variable named searchTerm with out defining it. That is just about an error-creating apply in any programming language.
Fail, fail, fail, McFaildypants.
The web hath spoken
OpenAI appeared to endure from the identical hubris that its AIs do. It confidently moved everybody to GPT-5 and burned the bridges again to GPT-4o. I am paying $200 a month for a ChatGPT Pro account. On Friday, I could not transfer again to GPT-4o for coding work. Neither might anybody else.
There was, nonetheless, only a tiny little bit of consumer pushback on the entire bridges burning factor. And by tiny, I imply the entire frickin’ internet. So, by Saturday, ChatGPT had a brand new possibility.
To get to this, go to your ChatGPT settings and activate “Present legacy fashions.” Then, because it has all the time been, simply drop down the mannequin menu and select the one you need. Word: this feature is just accessible to these on paid tiers. When you’re utilizing ChatGPT without spending a dime, you will take what you are given, and you may find it irresistible.
Ever because the entire generative AI factor kicked off at the start of 2023, ChatGPT has been the gold normal of programming instruments, a minimum of in response to my LLM testing.
Additionally: Microsoft rolls out GPT-5 across its Copilot suite – here’s where you’ll find it
Now? I am actually undecided. That is solely a day or so after GPT-5 has been launched, so its outcomes will most likely get higher over time. However for now, I am sticking with GPT-4o for coding, though I do just like the deep reasoning capabilities in GPT-5.
What about you? Have you ever tried GPT-5 for programming duties but? Did it carry out higher or worse than earlier variations like GPT-4o or GPT-3.5? Have been you in a position to get working code on the primary attempt, or GPT-4o did you need to information it by means of fixes? Are you going to make use of GPT-5 for coding or follow older fashions? Tell us within the feedback under.
You may observe my day-to-day mission updates on social media. You should definitely subscribe to my weekly update newsletter, and observe me on Twitter/X at @DavidGewirtz, on Fb at Facebook.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, on Bluesky at @DavidGewirtz.com, and on YouTube at YouTube.com/DavidGewirtzTV.
