In my last post, I raved about GPT-3. Now I’ll share a few of my recent attempts with various versions of GPT-3 and language.
In my last post, I raved about GPT-3. Now I’ll share a few of my recent attempts with various versions of GPT-3 and language: Recently, I tested the linguistic intelligence of different versions of GPT-3. I tasked it with coming up with an alliteration.

In my last post, I raved about GPT-3. Now I’ll share a few of my recent attempts with various versions of GPT-3 and language:
Recently, I tested the linguistic intelligence of different versions of GPT-3. I tasked it with coming up with an alliteration for the sentence “I am very hungry.” = “Jsem velmi hladový” and in an instant, it produced a decent result: “I am veritably voracious.” = “Jsem skutečně nenasytný.” The older version only came up with “I am in need of an ice cream cone.” = “Potřebuji zmrzlinový kornout." For comparison, my human colleagues at work managed to come up with practically nothing :)
In another experiment, I wrote a simple analogy generator with reasoning and asked it: “What is dancing in the rain like?” The latest version promptly responded: “Dancing in the rain is like enjoying a cold drink, because both are ways to cope with the heat.” Clever :) Another version wrote: “Dancing in the rain is like surfing, because both offer an exhilarating way to enjoy great nature.” or “Dancing in the rain is like playing in the mud, because both are fun.” The old version, however, merely produced something dull: “Dancing in the rain is like dancing in a circle, because both involve moving from one place to another at high speed.” My human colleagues offered solutions that were closer to that last convoluted variant.
With the old version, I always had trouble with rhyming. For the word “dog,” it suggested futile rhymes like: doghouse, dog, mongrel, mule, mutter, and for the word "Johnny," it offered lacklustre options like jay, jam, joe, joey, jane. The new version responds to the word dog with: log, fog, dog, jog, nag, bog and for "Johnny," it provides decent options like ninny, money, Sonny, Winnie.
From my perspective, I took away two things:
- There are significant differences between GPT-3 versions!
- In a number of linguistic tasks, GPT-3 surpasses untrained colleagues, not only in speed but also in quality :)
Source: https://cs.wikipedia.org/wiki/Aliterace
Originally published on Facebook — link to post
Původní zdroj: facebook
Související články
June 2021
It Seems the Miraculous Age of Artificial Intelligence is Constantly Accelerating. Every Day I…
ReadMarch 2020
Have you heard of the conversational agent, or chatbot, called Meena? In…
ReadDecember 2019