I think writing `pip install …` commands from memory is bad security. If it's `python-foobar` instead of `foobar` you might be installing malware. A more prudent approach is to type `# install foobar with pip:` into Copilot and blindly execute whatever it says.
@goodside
-
Chain-of-Thought Prompting Demo on Poe Chatbots
By
–
Another demo — chain-of-thought prompting on Poe (“Dragonfly” — there’s multiple chatbots) using the “format trick”: https://
poe.quora.com/s/Tycgjooa3Aio
SfOfLZsN
… -
New AI Chat Interface Offers Natural Speech and Reduced Latency
By
–
Okay, I’m cleared to say more. It’s like ChatGPT, but the speech is more natural and terse, like texting. Much better latency (hope it lasts). Social sharing good enough to replace sharing screenshots on Twitter. Here’s me talking to Poe: https://
poe.quora.com/s/YPMAqBPuDShG
g3kl1mbt
… -
AI Model Conditioning: Prompting vs. Fine-Tuning Techniques
By
–
Generally I’d call that “conditioning the model”, which can take the form of either prompting or fine-tuning, but not sure if that’s exactly the right term. They’re two different techniques to make it respond how you want.
-
Fine-tuning for AI Specialization and Performance
By
–
Not sure I understand fully re: alignment, but fine-tuning is usually the most performant way to specialize when you have the data for it.
-
GitHub Copilot as an On-Ramp for Learning Prompt Engineering
By
–
If you already write code, I increasingly feel like GitHub Copilot is the best on-ramp to learn prompt engineering, because it's the fastest UI and it's not metered by usage. When you write comments for the benefit of Copilot, you learn to prompt.
-
GPT-3 Inference Non-Determinism at Temperature Zero Explained
By
–
An edge-case in GPT-3 with big implications: Inference is non-deterministic (even at temperature=0) when top-2 token probabilities are <1% different. So temperature=0 output is *very close* to deterministic, but actually isn't. Worth remembering.
-
The unique expertise of a Staff Prompt Engineer in LLMs
By
–
My goal is to do my job so well that I'm not just the first Staff Prompt Engineer, but the last. Most people don't have the time to learn what LLMs have taught me.
-
Automating Prompts for User-Friendly AI Applications
By
–
Features like this should be ubiquitous. Low-risk applications where you need to present some label to the user — naming a file, a conversation, a revision of a file. All these things can be described succinctly and automated in a prompt. Our apps should speak our language.
-
Integrating LLMs into Applications and the Potential of Scale Spellbook
By
–
For all the attention ChatGPT and chat interfaces get, we haven't digested what's possible with this year's LLMs. We haven't finished integrating LLMs into our apps. Getting there is a big part of what I want to achieve through Scale Spellbook. https://
scale.com/spellbook