you want your coding models to have good taste, so we have fed them a vast dataset of sommelier wine gradings.
we've also contracted hundreds of local record store guys with deeply knowledgeable music taste spanning post-punk, classic jazz, early hip-hop, and deep-cut experimental vinyl. This has resulted in the model returning judgmental responses up to 23% more often which we are working on addressing.
maybe a bit, but 360 panoramic image still doesn't really address things out of direct line of sight. e.g. in a house, go through a door to a room, come back it's a different room :P
or even if you have a vast line of sight but a guy goes behind a tree
they are separate questions about the input. One question can be "is this a complaint?" and another "Should we flag this email to security" and a third "Is the sender a Bush era republican?"
90% of the {muse,grokbot,instinct,dots,...} fuss is just that your {aunt,cousin,neighbor's dad} probably doesn't have a good codex or claude code setup, and probably does not have a great local machine to run them from anyway.
So everyone is trying to give the aunts, cousins, neighbor's dads some of the agent capabilities that developers have been closer to.
That said, there's the other 10% here that is not necessarily new capability unlocks vs codex, but general product experience that can have some benefit to people already used to what the latest models can do
I'd assume it pulls at the very human desire to do less so you can spend your time as you want. Collectively, we are really good at making systems we don't understand and still have to exist in this world: Laws, taxes, internet check outs, etc. This is trying to flatten the curve between desire and result for things someone genuinely doesn't want to or doesn't have the time to become an expert in.
Pantone is not a color space. They are a supplier of physical color samples. Most pigments can be represented in a color space, but that representation differs based on illumination so it not unique. Some Pantone pigments, fluorescent colors in particular, cannot be represented by a color space at all!
Yup. This is a rabbit hole like time. Learn a little bit about it, know there's a staggering amount more and then any time you actually need it, check that you've agreed on as much detail as you needed for the task and not less.
The person inviting you to a picnic "next week" might need to know about Time Zones if they live some distance away. The requirement to update the CSS on the web site to match a new company logo might need to know about Colour Spaces. But that picnic invite doesn't care about Calendar systems or Leap Seconds, and the logo mandate doesn't care about Sub-surface scattering or a Quantum theory of light.
I think you'd want to remove e.g. knowledge of harry potter universe and ancient egypt. Training on a bunch of high quality java code bases is still likely to improve your python model.
Actually, it's shown that even general knowledge helps coding models because their input is natural language itself so they need to understand it well enough to even turn into code.
we've also contracted hundreds of local record store guys with deeply knowledgeable music taste spanning post-punk, classic jazz, early hip-hop, and deep-cut experimental vinyl. This has resulted in the model returning judgmental responses up to 23% more often which we are working on addressing.
reply