Toots from 2024-02-16

As someone who enjoyed X{ML,SLT, *} and RDF, I’m nonplussed with the idea that to get a JSONSchem…

As someone who enjoyed X{ML,SLT, *} and RDF, I’m nonplussed with the idea that to get a JSONSchema conforming response from an LLM I need to resubmit the failing response with an additional “please for real this time” prompt.

Mastodon Source 🐘

@darkuncle Definitely 💯

Mastodon Source 🐘

Good reason for pairing/working in proximity with a partner. Juniors onboarding understandably mi…

Good reason for pairing/working in proximity with a partner. Juniors onboarding understandably miss silent signals. They won’t even realize they should ask a senior because there’s no event to which they should react.

“Novices don’t know what is typical, so they have a hard time identifying what is atypical. Experts can quickly spot unusual events and detect deviations. And, they are able to notice when something that ought to happen, doesn’t.”

https://commoncog.com/an-easier-method-for-extracting-tacit-knowledge/

Mastodon Source 🐘

This communication gap is widened in distributed environments. Expecting juniors to immediately setup a video call with a senior asking “hey, I have no idea what’s going on and there is no data” can be a delicate topic and expectation. Depending on the organization, that behavior can either signal “proactively reaches out to unblock progress” or “fails to deeply investigate issues”.

Mastodon Source 🐘

IIRC https://learning.oreilly.com/library/view/inmates-are-running/0672326140/ has a section on creating empathetic error messages that’s helpful.

Expecting people to respond to a signal’s absence without informing them it should exist doesn’t set them up for success.

Mastodon Source 🐘

“Finally, consider the relatively newfound appreciation within AI research about how preexisting …

“Finally, consider the relatively newfound appreciation within AI research about how preexisting human biases can pollute the training data using within machine learning….For almost 50 years, the most introductory anthropology training has endeavored to instill a recognition that cultural differences and perceptions of otherness biases the observations of researchers.”

https://dl.acm.org/doi/10.1145/3383444