TOOLS

→ View original post on X — @ibmdata

IBM Launches Digital Self-Serve Co-Create Experience for AI Applications

By

@ibmdata

–

19 December 2022 15h10

We’re excited to introduce the new Digital Self-Serve Co-Create Experience (DSCE) from #IBM Build Lab: https://t.co/gGek0zvYht

^ a prescriptive, wizard-driven experience designed to onboard, scale and differentiate partner applications with embeddable #AI.
—#AIOps #MLOps pic.twitter.com/F81oBh9W7A
— IBM Data, AI & Automation (@IBMData) 19 décembre 2022

We’re excited to introduce the new Digital Self-Serve Co-Create Experience (DSCE) from #IBM Build Lab: https://
ibm.co/3Wpgbbn ^ a prescriptive, wizard-driven experience designed to onboard, scale and differentiate partner applications with embeddable #AI.
—
#AIOps #MLOps

FITM definition for Copilot’s cursor placeholder

By

–

19 December 2022 14h58

FITM = fill-in-the-middle, models trained to generate text to fill in a placeholder within the prompt rather than complete it from the end. For Copilot, the placeholder is the cursor.

Copilot’s stage play: a subtle art RLHF aims to replace.

By

–

19 December 2022 11h12

Nothing I’ve posted to Twitter will teach you as much as this prompt. Every Copilot completion is a tiny stage play for an LLM audience, with your file on stage and a backdrop curtain designed by a procedural script. A masterpiece of the subtle art form RLHF aims to replace.

Reverse-engineering GitHub Copilot: brilliant notes by @parth007_96

By

–

19 December 2022 10h22

See @parth007_96
’s brilliant notes on reverse-engineering GitHub Copilot here: https://
thakkarparth007.github.io/copilot-explor
er/posts/copilot-internals
…

GitHub Copilot’s implicit prompt engineering creates a competitive moat

By

–

19 December 2022 10h22

When you hit tab in GitHub Copilot, you’re FITM-completing a prompt of your file with an implicit comment header added, and it takes pages to describe what might be in that header. That’s prompt engineering. That’s a moat.

GPT-3/LLM prompts as assembly code, need prompt compilers

By

–

19 December 2022 10h22

I increasingly see GPT‑3/LLM prompts as assembly code, not as human interface. We shouldn’t be writing prompts, but prompt compilers. A template string is not a moat.

→ View original post on X — @benthompson

Passport developing solution for upcoming technical challenge

By

@benthompson

–

19 December 2022 1h17

Passport is working on a solution for that. Will take a bit but definitely something we think we can help with