In what ways is the agents.json file different from an OpenAPI Arazzo specification? Is it more native for LLM use? Looking at the example, I'm seeing similar concepts between them.
We've been in touch with Arazzo after we learned of the similarities. The long-term goal is to be aligned with Arazzo. However, the tooling around Arazzo isn't there today and we think it might take a while.
agents.json is meant to be more native to LLMs, since Arazzo serves other use cases than LLMs.
To be more specific, we're planning to support multiple types of sources alongside REST APIs, like internal SDKs, GraphQL, gRPC, etc.
Thanks, that's helpful. I agree there are many other sources REST APIs where this would be helpful. Outside of that I would be interested in understanding the ways where Arazzo takes a broader approach and doesn't really fit an LLM use case.
It's not that Arazzo can't work for LLMs, just that it's not the primary use case. We want to add LLM enabled transformations between linkages. Arazzo having to serve other use cases like API workflow testing and guided docs experiences may not be incentivized to support these types of features.
First place I usually go is the terms of service and what they are granting themselves rights to. Not excited about how broad this is "3.2 License: By using the Services, you hereby grant to Cognition, its affiliates, successors, and assigns a non-exclusive, worldwide, royalty-free, fully paid, sublicensable, transferable license to reproduce, distribute, modify, and otherwise use, display, and perform all acts with respect to the Customer Data as may be necessary for Cognition to provide the Services to you."
"as may be necessary for Cognition to provide the Services to you" kind of makes sense IMO. Does that mean they'll only use the license (note: they only get a license, not ownership) to provide services to you? Is it a restriction?
Yes, that clause/phrase restricts the company's rights with respect to their license to your data. Essentially, a clause like that is necessary for users to interact with the service. Makes sense when you think about it, how can they provide service if they can't use the data you provide them?
It's a pretty typical clause you'll see in most SaaS policies.
Source: I work for a SaaS, but I am not a lawyer, caveat emptor.
I want to pay for their product, but not enough that I have to ask my lawyer about the language. I did see that one of the features of the enterprise plan is custom terms, but that's not the plan I'm interested in.
I always wonder how enforceable these blanket rights would be in court. Didn’t Meta claim to own end users’ photos in the T&Cs back around 2009 and it got challenged and shot down (ianal)?
Original article that caused the outrage. In particular, the TOS did not say they owned your pictures, but it did give them a license that was quite broad, which included using your likeness in advertisements. However, the change that caused the outrage was that the license no longer expired on account deletion nor content removal.
I was looking into this for identifying other animals.
iNaturalist has a community that adds observations and identifies species. They have an API as well as a dataset for research https://www.inaturalist.org/pages/developers
Other CRM tools I've used will allow you to create groups/categories of contacts and set the recurrence to contact people in that group. You could similarly rate the group instead of individuals. Then the user could re-evaluate based on the group (friends, colleague, family, etc)
And as with any mental model there are potential pitfalls such as when you tell yourself your willpower has been depleted. You then have an excuse to slack off http://www.nirandfar.com/2016/11/the-way-you-think-about-wil.... I agree it's hard to make the right choice when your tired, but the way you think about it will also affect your behavior.
It is easiest for me to just pretend it does not exist. I guess it is sort of philosophical (again). When there is no will, decisions are made using a different system of values and alignment with goals. I don't need "will power" when my environment pushes me in the right direction and the choices, the ones I want are naturally aligned with multiple other aspects of my life and less healthy or negative choices are far out of alignment with that. It requires constantly remembering, setting, and working towards those goals (fitness, life, and other).
We obviously aren't just subject to the whims of our environment, we make choices and can decide things, but after a lot of reading on AI / neuroscience, and just being alive longer I am becoming convinced the environment and your perception of it is the single biggest factor. It goes beyond happiness toward fundamental outlook and beliefs.
Based on all of the responses to this comment I can see how someone would be completely confused on what they need to do to lose weight.
While admitting the rest of this thread is bonkers, I'll explicitly list the formula you should follow right now (science is always evolving):
Change in Body Stores = (Actual Calories In - Calories Not Absorbed) - (Resting Metabolic Rate + Thermic Effect of Eating + Physical Activity + Non-Exercise Activity Thermogenesis)
This is the more nuanced formula of calories in, calories out. Changing one variable in that equation can have an effect on the rest of the equation, which is why it appears calories is not equal to calories out. You can read about each variable here: http://www.precisionnutrition.com/metabolic-damage.
"Calories Not Absorbed" really got me thinking. While a food is labeled with their potential calories - the amount actually extracted from the food by your gut will vary significantly based on the composition of the food. The bioavailability of calories for example in a cookie versus some fibrous raw vegetable are going to differ significantly, being absorbed at different rates and to differing degrees of completeness.
Here is an interesting article with an important take away: "In general, it seems that the more processed foods are the more they actually give us the number of calories we see on the box"
https://blogs.scientificamerican.com/guest-blog/the-hidden-t...
I found this recently [1] suggesting that 15-18% of calories from peanuts are excreted. It's probably more for me since they give me digestive problems and that's what made me curios about the subject too.
So I guess eating processed food vs food that's hard to digest actually matters a decent bit if you're counting calories (10-15% of your calories is not insignificant - that's almost half of what you're trying to cut on a calorie restriction diet)
Calories not absorbed has also made me think about diets like the raw food diet. Eating raw uncooked vegetables is going to reduce the calories you absorb while taking up more volume in your stomach.
On top of that I just tried to sign up for an account. I don't want to connect Google or Facebook so I tried to use their registration. It wasn't possible to do in Chrome. I decided try the nytimes.com homepage and I could probably sign up there but the registration is over an insecure http page.
I switched to Safari and was able to create an account. Went back to Chrome and still couldn't login. Not worth it.
The part about calling you up when it was clear you wanted to give them your info was what really concerned me. It's an easy way to scare your customers away.
As he said, the creep factor was high. If you were to do something like that it should be clear that your information is being captured or give you the ability to opt out right next to your phone number. That would still be a LinkedIn like deceitful UX experience but slightly better.
I purchased a bluetooth receiver for my car last year since I already had a headphone size cord to plugin to my phone. The same thing could be used for your now obsolete headphones. Although all I could find was the refurbished version. https://www.amazon.com/Etekcity-Bluetooth-NFC-Enabled-Certif...
Now you just have to carry your phone plus a bluetooth receiver to plug into!
