with skills, model can easily learn the jargon.

exactly. to mind-meld with your AI, you will have to use/understand quite dense language.

Would love some critique of my thoughts.

How I used Codex, FlowDeck, and Loopback to automate testing of Voice Interactions for my Voice-First App: https://www.elicited.blog/posts/teaching-codex-to-test-a-voi...

I am not an expert in either ML or AI, so appreciate expert feedback on my thoughts and learnings.

haven't succeeded at GEPA yet..

anyone working on an dspy optimizer for this?

This is a DSPy optimizer, built by the DSPy core team. Just wait for open sourcing.

okhat is a great way to shorten your name gave me a good laugh

they’ve already written one! see omar’s x account for details!

Here's a link to a repost Omar made referencing it: https://x.com/DSPyOSS/status/1950733300420510006

make a video on how to "take" this course

There are several videos in the link that does this.

Where?! I only see intro videos to each lesson. No actual "lesson" being shown.

this is a good idea

we will update the top intro video to show how to actually get into the course

RE: product-focused moves

These are tentacles that AGI will need.

Yeah, AGI needs a VS Code fork.

wow, one year back, I had made a prediction to a friend that this is the direction that Starlink will head in. I was thinking it would proceed like this:

1. provide internet. 2. provide CDN. 3. Edge Compute. 4. Full-on cloud.

These guys see to be focussing on what is basically offline processing (AI training).

More like, these guys will be focused on parting VCs from their money.

Datacenters in space makes no sense at all. Even ignoring the huge cost of sending hardware there in the first place, cooling is a massive issue in space. No medium to sink heat into means the only way to cool anything is by running water through giant infrared radiators. Not ideal when cooling is the largest bottleneck in scaling datacenters. Note that they would also have to dissipate the large amounts heat their datacenter satellite gets from being exposed to the Sun.

Also disregard the cost it takes to send a technician for maintenance, of updating hardware, etc.

> Also disregard the cost it takes to send a technician for maintenance, of updating hardware, etc.

This won't happen. If a satellite fails they will just write it off. Maintenance would be more expensive than depreciation

They’re proposing a multi-kilometer sized satellite, though. That’s more akin to demolishing an entire datacenter when something important fails.

How is it even feasible to build that?

Interesting. I was assuming that cooling is basically a non-issue in space. I'll need to read up on that.