ChatGPT study suggests its LLMs are getting dumber at some tasks
GPT-3.5 and GPT-4 – the models at the heart of OpenAI's ChatGPT – appear to have got worse at generating some code and performing other tasks between March and June this year. That's according to experiments performed by computer scientists in the United States. The tests also showed the models improved in some areas.
"We evaluated ChatGPT's behavior over time and found substantial differences in its responses to the same questions between the June version of GPT-4 and GPT-3.5 and the March versions," Academics at Stanford and the University of California, Berkeley tested the models' abilities to solve mathematical problems, answer inappropriate questions, generate code, and perform visual reasoning. They found that over the course of just three months, GPT-3.5 and GPT-4's performance fluctuated radically.
Danmark Seneste Nyt, Danmark Overskrifter
Similar News:Du kan også læse nyheder, der ligner denne, som vi har indsamlet fra andre nyhedskilder.
What to Know About Claude 2, Anthropic's Rival to ChatGPTClaude 2, built by Anthropic, is the latest large language model AI to challenge OpenAI's ChatGPT.
Læs mere »
We asked ChatGPT to write a poem about Northamptonshire and its pretty good'Northamptonshire, where the meadows dance and history weaves its timeless trance'
Læs mere »
AI: Facebook owner Meta announces its rival to ChatGPT will be free to useThis version of the model is trained on 40% more data compared with Llama 1, according to Meta.
Læs mere »
In an effort to surpass ChatGPT, Meta is open-sourcing its large language AI modelThe possibility for more AI tools, for free from Meta.
Læs mere »
Apple is reportedly working on a ChatGPT rival – but you won't see it anytime soonAn industry movement it can't ignore
Læs mere »
'ChatGPT's evil twin' WormGPT is devoid of morals and just €60 a month on the darkwebCybersecurity expert at NordVPN issues warnings over the new darkweb AI chatbot phenomenon.
Læs mere »