Some builders say they’ve had largely optimistic experiences with GPT-5 to this point. Jenny Wang, an engineer, investor, and creator of the private styling agent Alta, advised WIRED the mannequin seems to be higher at finishing complicated coding duties in a single shot than different fashions. She in contrast it to OpenAI’s o3 and 4o, which she makes use of ceaselessly for code technology and simple fixes “like formatting, or if I need to create an API endpoint much like what I have already got,” Wang says.
In her checks of GPT-5, Wang says she requested the mannequin to generate code for a press web page for her firm’s web site, together with particular design parts that will match the remainder of the location’s aesthetic. GPT-5 accomplished the duty in a single take, whereas previously, Wang would have needed to revise her prompts in the course of the course of. There was one important error, although: “It hallucinated the URLs,” Wang says.
One other developer, who spoke on the situation of anonymity as a result of their employer didn’t authorize them to talk to the press, says GPT-5 excels at fixing deep technical issues.
The developer’s present interest mission is writing a programmatic community evaluation software, one that will require code isolation for safety functions. “I mainly introduced my mission and a few paths I used to be contemplating, and GPT-5 took all of it in and gave again just a few suggestions together with a practical timeline,” the developer explains. “I’m impressed.”
A handful of OpenAI’s enterprise companions and clients, together with Cursor, Windsurf, and Notion, have publicly vouched for GPT-5’s coding and reasoning expertise. (OpenAI included many of those remarks in its personal blog post saying the brand new mannequin.) Notion additionally shared on X that it’s “quick, thorough, and handles complicated work 15 p.c higher than different fashions we’ve examined.”
However inside days of GPT-5’s launch, some builders had been weighing in on-line with complaints. Many stated that GPT-5’s coding talents appeared behind the curve for what was purported to be a state-of-the-art, ultra-capable mannequin from the world’s buzziest AI firm.
“OpenAI’s GPT-5 is excellent, but it surely looks as if one thing that will have been launched a yr in the past,” says Kieran Klassen, a developer who has been constructing an AI assistant for electronic mail inboxes. “Its coding capabilities remind me of Sonnet 3.5,” he provides, referring to an Anthropic mannequin that launched in June 2024.
Amir Salihefendić, founding father of the startup firm Doist, said in a social media post that he’s been utilizing GPT-5 in Cursor and has discovered it “fairly underwhelming” and that “it’s particularly dangerous at coding.” He stated the discharge of GPT-4 felt like a “Llama 4 second,” referring to Meta’s AI mannequin, which had additionally disenchanted some folks within the AI neighborhood.
On X, developer Mckay Wrigley wrote that GPT-5 is a “phenomenal on a regular basis chat mannequin,” however in relation to coding, “I’ll nonetheless be utilizing Claude Code + Opus.”
Different builders describe GPT-5 as “exhaustive”—at instances useful, however usually irritating in its long-windedness. Wang, who was happy total with the frontend coding mission she assigned to GPT-5, says that she did discover that the mannequin was “extra redundant. It clearly may have provide you with a cleaner or shorter resolution.” (Kapoor factors out that the verbosity of GPT-5 might be adjusted, in order that customers can ask it to be much less chatty and even do much less reasoning in trade for higher efficiency or cheaper pricing.)
