Create Post “2025-01-13-i-built-an-ai-prototype-that-can-participate-in-our-internal-meetings-in-a-week” #64
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…in-our-internal-meetings-in-a-week”
added 9 commits
January 14, 2025 12:29
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
…in-our-internal-meetings-in-a-week”
|
|
||
| I'm not quite satisfied with how AI integrations in meetings are mostly about summarising things after the fact. The process of ensuring that a meeting goes well as it happens is far more valuable than a summary. It's about ensuring things stay focused, and the right information and context is available to all participants. | ||
|
|
||
| Today's AI can hear you speak, understand context, and talk back naturally. Here's how I built this in about a week. |
There was a problem hiding this comment.
Suggested change
| Today's AI can hear you speak, understand context, and talk back naturally. Here's how I built this in about a week. | |
| Today's AI can hear you speak, understand context, and talk back naturally. Here's how I built <an AI bot that can join etc> in about a week. |
Might be easier to follow if it's repeated twice, once here and then the video example.
|
|
||
| _video demo goes here_ | ||
|
|
||
| LLMs (Large Language Models) are mainstream because of interfaces like ChatGPT - you type something, wait a bit, and get text back. Far fewer people know that models can also natively work with audio. They can process speech directly, understand the nuances of conversation, and even respond with natural-sounding voice. The challenge is: how do we actually plug this intelligence into our existing tools? |
There was a problem hiding this comment.
This paragraph seems redundant. Could combine just They can process speech directly, understand the nuances of conversation, and even respond with natural-sounding voice. with the paragraph above.
| - Can potentially handle meeting-related tasks like setting reminders or assigning action items | ||
| - So many more possibilities actually. More on this later when I wax philosophical at the end. | ||
|
|
||
| Let me give you a sketch of how I made this. |
There was a problem hiding this comment.
a sketch gets repeated.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Automatically generated by Decap CMS