I realize itās probably a toy example but specifically for ācatsā you could achieve the similar results by running a thesaurus/synonym-set on your stem words. With the added benefit that a client could add custom synonyms, for more domain-specific stuff that the LLM would probably not know, and not reliably learn through in-prompt or with fine-tuning. (Although iād argue that if iām looking for cats, I donāt want to also see videos of tigers, or based on the āunderstandingā of the LLM of what a cat might be)
For the labeling of videos itself, the most valuable labels would be added by humans, and/or full-text search on the transcript of the video if applicable, speech-to-text being more in the realm of traditional ML than in the realm of GenAI.
As a minor quibble your use case of GenAI is not really āGenerativeā which is the main thing itās being sold as.
fosstodon is the programming dot dev of mastodon and I mean that in every negative way you can imagine
your posts all give me slimy SEO vibes and you havenāt shown any upward trajectory since claiming that only generative AI lacks a separation between code and data (fucking what? seriously, think on this) so youāre getting trimmed
I just ended up throwing the name into a search engine (one of those boring old actually search engine things; how pedestrian of me)
Iām Curtis āOvidā Poe. Iāve been building software for decades. Today I largely work with generative AI, Perl, Python, and Agile consulting. I regularly speak at conferences and corporate events across Europe and the US.
I realize itās probably a toy example but specifically for ācatsā you could achieve the similar results by running a thesaurus/synonym-set on your stem words. With the added benefit that a client could add custom synonyms, for more domain-specific stuff that the LLM would probably not know, and not reliably learn through in-prompt or with fine-tuning. (Although iād argue that if iām looking for cats, I donāt want to also see videos of tigers, or based on the āunderstandingā of the LLM of what a cat might be)
For the labeling of videos itself, the most valuable labels would be added by humans, and/or full-text search on the transcript of the video if applicable, speech-to-text being more in the realm of traditional ML than in the realm of GenAI.
As a minor quibble your use case of GenAI is not really āGenerativeā which is the main thing itās being sold as.
Removed by mod
fosstodon is the programming dot dev of mastodon and I mean that in every negative way you can imagine
your posts all give me slimy SEO vibes and you havenāt shown any upward trajectory since claiming that only generative AI lacks a separation between code and data (fucking what? seriously, think on this) so youāre getting trimmed
I just ended up throwing the name into a search engine (one of those boring old actually search engine things; how pedestrian of me)
ah.
back when I used the wider fediverse more frequently I had fosstodon on mute for a significant amount of time
glad to know itās still Like That