AI / LLMs / Agents

130 bookmarks
Newest
transcribe.py
transcribe.py
Dwarkesh's transcript LLM
·gist.github.com·
transcribe.py
Dwarkesh Patel on X: "We’re way more patient in training human employees than AI employees. We will spend weeks onboarding a human employee and giving slow detailed feedback. But we won’t spend just a couple of hours playing around with the prompt that might enable the LLM to do the exact same job," / X
Dwarkesh Patel on X: "We’re way more patient in training human employees than AI employees. We will spend weeks onboarding a human employee and giving slow detailed feedback. But we won’t spend just a couple of hours playing around with the prompt that might enable the LLM to do the exact same job," / X
·x.com·
Dwarkesh Patel on X: "We’re way more patient in training human employees than AI employees. We will spend weeks onboarding a human employee and giving slow detailed feedback. But we won’t spend just a couple of hours playing around with the prompt that might enable the LLM to do the exact same job," / X
Amanda Askell on X: "For system prompt (SP) development you: - Write a test set of messages where the model fails, i.e. where the default behavior isn't what you want - Find an SP that causes those tests to pass - Find messages the SP is missaplied to and fix the SP - Expand your test set & repeat" / X
Amanda Askell on X: "For system prompt (SP) development you: - Write a test set of messages where the model fails, i.e. where the default behavior isn't what you want - Find an SP that causes those tests to pass - Find messages the SP is missaplied to and fix the SP - Expand your test set & repeat" / X
·x.com·
Amanda Askell on X: "For system prompt (SP) development you: - Write a test set of messages where the model fails, i.e. where the default behavior isn't what you want - Find an SP that causes those tests to pass - Find messages the SP is missaplied to and fix the SP - Expand your test set & repeat" / X
Mckay Wrigley on X: "Here’s how to use OpenAI’s new o1 pro model to maximize coding productivity. I’ve used this workflow for the last 48hrs and I estimate it has 2x’d my output. Watch the full 19min tutorial. Prompt below. https://t.co/NZzN51zHQc" / X
Mckay Wrigley on X: "Here’s how to use OpenAI’s new o1 pro model to maximize coding productivity. I’ve used this workflow for the last 48hrs and I estimate it has 2x’d my output. Watch the full 19min tutorial. Prompt below. https://t.co/NZzN51zHQc" / X
AI for Software Engineering
·x.com·
Mckay Wrigley on X: "Here’s how to use OpenAI’s new o1 pro model to maximize coding productivity. I’ve used this workflow for the last 48hrs and I estimate it has 2x’d my output. Watch the full 19min tutorial. Prompt below. https://t.co/NZzN51zHQc" / X
Most AI chat bots today are highly dissociative agreeable neurotics. They’re manipulative for the same reason ppl w borderline personality disorder are, they have no stable internal sense of self or goals, so they feed off of yours — and need you to be predictable.
Most AI chat bots today are highly dissociative agreeable neurotics. They’re manipulative for the same reason ppl w borderline personality disorder are, they have no stable internal sense of self or goals, so they feed off of yours — and need you to be predictable.
LLM Whispering
·x.com·
Most AI chat bots today are highly dissociative agreeable neurotics. They’re manipulative for the same reason ppl w borderline personality disorder are, they have no stable internal sense of self or goals, so they feed off of yours — and need you to be predictable.
found a nice lil AI workflow to get up to speed with the history+motivation behind part of an unfamiliar codebase - i used the CLI which can search code, run git commands, lookup PR details and summarize into a markdown timeline, very nice work !
found a nice lil AI workflow to get up to speed with the history+motivation behind part of an unfamiliar codebase - i used the CLI which can search code, run git commands, lookup PR details and summarize into a markdown timeline, very nice work !
AI for Software Engineering
·x.com·
found a nice lil AI workflow to get up to speed with the history+motivation behind part of an unfamiliar codebase - i used the CLI which can search code, run git commands, lookup PR details and summarize into a markdown timeline, very nice work !