Generative AI & LLMs in practice
An interesting story from @christogrozev
Chinese Deepseek AI twists his story and starts feeding him Russian propaganda, and not only gets it wrong, tries to manipulate him when challenged. https://t.co/Q8qfj0Yl3l
Bricktop_NAFOx.comIn Shiva, we find the perfect metaphor for Artificial Intelligence: a force that is simultaneously still and active, formless and structured, transformative and terrifying.
with only a couple of prompts, Gemini CLI can convert a messy folder containing hundreds of notes into a neatly named, well-structured, cross-linked Obsidian knowledge graph
all in about half an hour and at minimal cost.
from r/singularity/Ryoiki-Tokuiten https://t.co/SLhirQYB6L
Rohan Paulx.comKey findings:
45% of all AI answers had at least one significant issue.
31% of responses showed serious sourcing problems – missing, misleading, or incorrect attributions.
20% contained major accuracy issues, including hallucinated details and outdated information.
Gemini performed worst with significant issues in 76% of responses, more than double... See more
45% of all AI answers had at least one significant issue.
31% of responses showed serious sourcing problems – missing, misleading, or incorrect attributions.
20% contained major accuracy issues, including hallucinated details and outdated information.
Gemini performed worst with significant issues in 76% of responses, more than double... See more