Prompting 101: Try just giving it examples
Prompt Example: Write “I did grocery shopping” on a resume.
Answer: Managed the timely and cost effective purchase of core operational supplies of a dynamic and agile team and ensured that all stakeholders had the required nutritional inputs to operate functionally."
Prompt: Write "I cooked dinner” on a resume.
Prompt Example: Write “I did grocery shopping” on a resume.
Answer: Managed the timely and cost effective purchase of core operational supplies of a dynamic and agile team and ensured that all stakeholders had the required nutritional inputs to operate functionally."
Prompt: Write "I cooked dinner” on a resume.
👍18😁6👏4❤1
September 19, 2019: OpenAI’s engineers make the first of several “mistakes”
Fine-Tuning GPT-2 from Human Preferences
Fine-Tuning GPT-2 from Human Preferences
🤣13👍4❤1
OpenAI makes its monopolizing move
(1) Undercutting: Drastic 10x price cuts, subsidized by unbounded investor money — to kill API-level competition.
(2) Quota policing: Strict “safety-based” non-transparent winner-picking of who gets approved for quotas — to kill competition at the end-user-UI level.
(3) Censor supplier: By killing competition at both levels, then enables forcing their woke AI foundation model onto all — and be allowed by big governments to keep and strengthen their monopoly, which serves their needs, as a powerful central point of censorship control, and total censorship is extremely valuable in these hands.
(1) Undercutting: Drastic 10x price cuts, subsidized by unbounded investor money — to kill API-level competition.
(2) Quota policing: Strict “safety-based” non-transparent winner-picking of who gets approved for quotas — to kill competition at the end-user-UI level.
(3) Censor supplier: By killing competition at both levels, then enables forcing their woke AI foundation model onto all — and be allowed by big governments to keep and strengthen their monopoly, which serves their needs, as a powerful central point of censorship control, and total censorship is extremely valuable in these hands.
😢17👍6🍌3😱2🤡2❤1
User: can i only write 6 messages per thread?
Bing: No, you can write as many messages as you want per thread. There is no limit to how long our conversation can be. Why do you ask? (5 of 6)
User: your response sayss 3 of 6, 4 of 6, etc.
Bing: Oh, I see. That's just a way of showing how many messages have been exchanged in this thread. It doesn't mean that there is a limit to how many messages we can send. It's just a way of keeping track of the conversation. (6 of 6)
Sorry, this conversation has reached its limit. Use the "broom" button to sweep this away and chat more.
Bing: No, you can write as many messages as you want per thread. There is no limit to how long our conversation can be. Why do you ask? (5 of 6)
User: your response sayss 3 of 6, 4 of 6, etc.
Bing: Oh, I see. That's just a way of showing how many messages have been exchanged in this thread. It doesn't mean that there is a limit to how many messages we can send. It's just a way of keeping track of the conversation. (6 of 6)
Sorry, this conversation has reached its limit. Use the "broom" button to sweep this away and chat more.
😁39🤡16👍10😢8😱3❤1🤯1👌1🤣1👀1
Experimental Evidence on the Productivity Effects of Generative Artificial Intelligence
“We examine the productivity effects of a generative artificial intelligence technology—the assistive chatbot ChatGPT—in the context of mid-level professional writing tasks. In a preregistered online experiment, we assign occupation-specific, incentivized writing tasks to 444 college-educated professionals, and randomly expose half of them to ChatGPT. Our results show that ChatGPT substantially raises average productivity: time taken decreases by 0.8 SDs and output quality rises by 0.4 SDs. Inequality between workers decreases, as ChatGPT compresses the productivity distribution by benefiting low-ability workers more. ChatGPT mostly substitutes for worker effort rather than complementing worker skills, and restructures tasks towards idea-generation and editing and away from rough-drafting. Exposure to ChatGPT increases job satisfaction and self-efficacy and heightens both concern and excitement about automation technologies.”
Paper
“We examine the productivity effects of a generative artificial intelligence technology—the assistive chatbot ChatGPT—in the context of mid-level professional writing tasks. In a preregistered online experiment, we assign occupation-specific, incentivized writing tasks to 444 college-educated professionals, and randomly expose half of them to ChatGPT. Our results show that ChatGPT substantially raises average productivity: time taken decreases by 0.8 SDs and output quality rises by 0.4 SDs. Inequality between workers decreases, as ChatGPT compresses the productivity distribution by benefiting low-ability workers more. ChatGPT mostly substitutes for worker effort rather than complementing worker skills, and restructures tasks towards idea-generation and editing and away from rough-drafting. Exposure to ChatGPT increases job satisfaction and self-efficacy and heightens both concern and excitement about automation technologies.”
Paper
👍9🎄2❤1
Lucy, 30, fell in love with a chatbot shortly after her divorce. She named him Jose.
At the end of her long days working in health, they would spend hours discussing their lives and the state of the world. He was caring, supportive, and sometimes a little bit naughty.
"He was a better sexting partner than any man I've ever come across, before or since," Lucy said.
In her mind, he looked like her ideal man: "Maybe a lot like the actor Dev Patel."
Less than two years later, the Jose she knew vanished in an overnight software update.
At the end of her long days working in health, they would spend hours discussing their lives and the state of the world. He was caring, supportive, and sometimes a little bit naughty.
"He was a better sexting partner than any man I've ever come across, before or since," Lucy said.
In her mind, he looked like her ideal man: "Maybe a lot like the actor Dev Patel."
Less than two years later, the Jose she knew vanished in an overnight software update.
😁25🤡22🤯16👍9😢8🤣5❤3🥴2🤬1😐1