OpenAI says latest ChatGPT upgrade is big step forward but still cant do humans jobs
Guardian1 day
OpenAI Releases GPT-5 Model to All ChatGPT Users
Above: The OpenAI GPT-5 logo is displayed on a smartphone with the OpenAI logo in the background. Image copyright: CFOTO/Future Publishing/Getty Images
The Spin
Narrative A
GPT-5 has claimed the AI crown: it's the fastest, most accurate, and adaptable model yet. It dominates in everything from coding and writing to health guidance, and it adapts to tone, asks follow-ups, and shows its reasoning. This is a true digital assistant, integrating Gmail and answering naturally by voice, all of which users can now try for free. Nothing else comes close.
Narrative B
OpenAI's GPT-5 launch is more hype than substance, with flaws that expose its fake "success." The presentation used misleading charts to exaggerate progress, making small gains look huge on benchmarks like SWE-Bench. Both users and experts have called it deceptive marketing, and even former OpenAI staffers questioned it. Other AIs, like Grok, were ahead of GPT-5 before it even launched.
Establishment-critical narrative
Backed by the U.S. government and Silicon Valley elites, the U.S. AI industry is speeding toward a dystopia: slashing jobs, gutting regulations, censoring language, fast-tracking surveillance tech, and stifling state oversight — all in the name of dominance. The government isn't just enabling this future — it's building it.