Applying fork/join model and git-style cherry picking to AI conversations

In this post we introduce using the fork/join concurrency pattern combined with the git-style cherry picking to manage and use LLM conversations.

These are loose conceptual connections, so please put down the pitchfork (pun intended).

Just as in git you can cherry-pick a commit from one branch to create a new head on another branch, you can pick conversations across sessions (including between different models) to build context to drive LLM conversations.

You can also create a fork of a session, this creates a parallel set of messages that are detached from, ie forked off the main session within which they run.

You can create new messages that join an existing fork.

This is a nice capability, the degree to which it will prove useful is yet to be determined. One of the possibilities is giving the user an ability to create long term "memory" from AI conversations and being able to easily reuse that memory (set of messages) without the need to rebuild context.

The ability to label forks is especially helpful in letting user know what the fork represents and thus offers the potential of greater utility. Below is a demo of this feature:

Comments

Intelligent Workspace: Managing your AWS Cloud Console via AI

Continuing in our series on the "Intelligent Workspace" as an alternative the the chatbot form factor, we have added another demo showcasing the versatility of the environment.

Where do we go from here? Some thoughts and speculation.

A lot of technologist are rightfully fretting about what the future holds for tech careers, especially in software developer roles. Perhaps it is time to think less about what tab-tab-go programming would mean for the future of developer roles and rather how those existing skill-sets could be leveraged in an AI world. There is tremendous potential in reorienting technologists from a focus on churning out the next app from an IDE and towards thinking in a more holistic manner about how to leverage what already has been built out both in terms of software and infrastructure. The past 30 yrs or so of the tech industry has been a ginormous build-out of technological capability. We in the industry may not have seen it that way since we have been the ones engaged in the build-out process. In other words we have seen the build-out primarily as just our jobs, and less as a process perhaps with a terminal date. I wouldn't go so far as saying the build-out is complete by any means, but it s...

Human + Bot Collaboration via Automated UI Generation Part 2

Today we demo a simple expense reporting application that is generated on the fly by AI and used by a human...call it Just-In-Time (JIT) app creation.

Codesolvent Blog

Search This Blog