@panossakalakis - just stubled across https://t.co/ffUbisSxSG - LOOKS INCREDIBLE!
I would love to set it up, but checkout doesn't seem to be working (in the US at least).
After 1 year of hearing about dspy, being excited about dspy, telling my coworker that we should try and learn dspy, telling @_rchaves_ that I will try dspy... but not trying dspy... even skimming the docs of dspy (3 to 4 times).. this presentation from @lateinteraction is what convinced me it was worth carving out time and learn it: https://t.co/7fQMrXTAbe
I'm not sure why, my guess is that I could smell the craftmanship.
The Pitfalls of Reasoning for Instruction-Following in LLMs
If you're dev using reasoning models, read this one.
Lots of great insights and mitigation tactics.
Here are my notes:
I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder.
You can download the workflow for free (link in comment)
AI Agents vs. Agentic AI
Interesting paper summarizing distinctions between AI Agents and Agentic AI.
It also talks about the key ideas, solutions, and the future.
Here are my notes:
@mymind@niieani@mymind "no API anytime soon..." Is this still the stance? I ask mostly for a single reason - writing an https://t.co/mugGcVNddt plugin to seamlessly integrate mymind remembering w/ my "exocortex" vault. ie a markdown list of the URLs I saved today, click to open in mymind...
Curious about recommender models?
Interested in endowing models from other domains with some of their superpowers?
Please join me on a whirlwind tour of 6 recsys architectures!
>> a thread ๐งต <<
https://t.co/8B2l6yM6fn
QAnon failed to infect in Japan, it was "too naive". Maybe instead of stopping spread of misinfo, we propagate more sophisticated conspiracies to develop stronger collective mental immune system? Fits nicely with @nealstephenson "Fall, or Dodge in Hell"
Will future historians and computer science researchers refer back to #QAnon as the first successful large-scale hybrid botnet, with both human and machine bot nodes?
So this is interesting. Let me break this down a bit:
NeonRevolt, a prominent Q-follower who literally wrote a book about it; posted this blind item, from a celebrity gossip site, that suggests someone is trying to sell the Q account for $1 million on the darknet.
Is it strange that I woke up with shadows of a dream where I was developing a systems view of exponentially asymmetric multi-agent information ecologies and spent my morning reading time reviewing epistemology and Davenport/Prusak?
@mooneydev Regarding โThe Framework Myth: 1) any thoughts on its applicability to the current spate of โplatformโ focus in many companies and 2) any good research that expands or backs up the organizational dynamic downside?