adamloving

It's reimbursement for Llama usage, and Meta is hoping you'll provide feedback on how Llama works for your scenario.

Not that I know of for Llama... but checkout https://forwork.meta.com/meta-for-education/

Great question, I'll check on that.

Yes

Meta wants feedback from startups on how Llama can be improved.

Is your business incorporated? I'm checking on whether contractors count towards the 1 developer requirement.

Let me check on that just to be sure.

Yes. You will just need to document how much of your OpenRouter bill was for Llama usage (like provide screenshots if its not broken down on your invoices or receipts).

Quick summary: Apply for up to $6K reimbursement per month for up to 6 months for Llama usage (wherever you use it). Incorporated startups with less than $10 million USD in funding are eligible. (disclosure: I work at Meta as Llama Partner Engineer)

This is really cool actually. I like how it uses the personas to query the LLMs from different angles. And 250 “queries” for free? That’s amazing value and impressive parallelism . Nice job guys!

Nope, you have control over what gets sent. Only the text after the command "please" (and previous commands and variables you've explicitly approved) are sent. You'd have to explicitly type "using my secret x". Your zshell history is not sent. Also, the only server involved is OpenAI's server (there's no Magic Shell server to fear - yet ;) )

I downloaded the mac app, configured a virtual device to send the system output to the "Krisp Speaker" and verified that it cuts most of the music out of what I'm listening to, leaving only the voice (at a some what degraded quality). I wish I could configure it _cancel_ ambient noise, not just remove it from the input signal.

Yeah, name and other attribute lookup is feasible (and seems inevitable). Also, this prototype only claims to take a snapshot and submit it. Needs to perform the check in realtime against video input.

That's what caught my eye as well. Wondering if it is boolean or perhaps decimal. Mustache: 0.13

I was one of them. We had many spirited discussions. TA was completely transparent about what was going on and we tried hard to find an angle to make it work. I look forward to future hacking with the others.

I'll come back and post a link to the video afterwards. If I forget, email me using freelance /at/ adamloving.com

I don't know for sure (I started out as a C++ developer, but I'm a web dev now) - but I'd suspect there is a lot of work out there. A better way to test might be to go to a local developer meet up specific to your skills and ask people where they work. I'd be surprised if there wasn't plenty of work to be had.

Thanks for the tip!

Thanks @rietta!

Thanks for sharing your story. While I dislike doing little bits of work (couple hours here and there), it's great when the work finds you, and you're on good working terms. A couple of times, I've had a M-W-F setup (on site with a client 3 days a week) - for me that is perfection.

Ha, you're right - I didn't notice the contradiction. I guess we'd all like to work on absolutely fascinating stuff for about 4 hours a day.

Thanks @t0mk! I've noticed that devs who've had to be "in control of their commitments" do a much better job planning, estimating, and setting realistic expectations.

Would you consider becoming a freelance software developer? Why or why not?

I didn't read closely, but looks like an ES6 version of angular.

Good points, here's a direct link to the response summary:

https://docs.google.com/forms/d/1a76QHt4-r-ow1FoNfi4jyTSygET...

I added it to the front of the survey as well.

I removed Seattle from the document title.

Thanks everybody! 95 responses so far. Very helpful.

That's a funny idea. I love it!

I think my usage will shift to Flickr as Instagram becomes more integrated with Facebook.

There are so many people and companies interested in the gamification of health, surely someone will snap this up.

Feels like a manifesto for the freedom of knowledge workers, love it!