back
user profile
CrypticShift
1,036karma·560submissions·November 1, 2022
recent activity (560 total)
comment
Yes, more opaque and unpredictable for sure, but I don’t think it deepens the problems of curation. I believe it is solution. : you trade predictability/transparency for smarter /non-linear …
comment
I think LLMs could definitely help us stop treating large piles as "lists" (to be completed). You can just "dialogue" with it through Chat. And if the AI has access to your recent …
comment
Now we need next gen GPT to automate "prompt engineering" itself. I guess this means being able to 1- Better "understand" your personal way/style of communicating and translat…
comment
I like this visualization https://www.visualcapitalist.com/all-of-the-worlds-money-and... . Maybe at least it will help show the difficulty in "counting" money.…
comment
This goes in line with the “Open” in OpenAI. However, this is a "controlled" sort of openness, and the problem of trust with their receding "real" openness does not encourage me to…
comment
Yeah, the samples are short and "cliche", I agree. Impressive is subjective : creating that from text is already impressive for me. Also, when I said copyright is limiting, I was thinking a…
comment
MusicLM [1] is the most impressive demo I've seen yet. The problem is we only have access to selected examples (=demo) so we don't know how it performs "on average". IMO, for music…
comment
So many are saying this is a rip-off of Notion. what is Notion? If Notion as a powerful Wiki+DB combo, then this is not a copy at all. If Notion as a slick block-based wiki, then this is so general a …
comment
IMO if this gets better, it can be useful with the expanded GPT context window:
Imagine you can automatically create a sort of "wizard" to guide decisions based on the content of any docume…
comment
Soil carbon [1] is related to soil health everywhere. We really should look more often, beyond forests, to how our built environment and conventional agriculture are hindering carbon sequestration on …
comment
the TaxGPT example in the GPT-4 Developer Livestream [1] was powerful. I'm hoping (soon?) for a Microsoft 365 assistant that can do the same trick on ALL your MS cloud data (docs/files/…
comment
> eye strain and digital detox Aren’t e-readers supposed to solve these two? They do for me anyway.
comment
Excellent! I'd love to see a script that sends a list of "descriptions" (1-100 words) to ChatGPT and directly gives you back a ready-made (embedding vectors closeness) map in a (textual…
comment
How do these compare to the recent Default ("turbo") vs legacy" (for plus/pro) modes? If "turbo" is "gpt-3.5-turbo", how to access the (better?) "legacy&qu…
comment
https://archive.ph/upP1d
comment
What kind of data ? could you share some of these stealth startups ? If you ask me, a simple Chat-GPT like interface for all my PIM (bookmarks/Notes/annotations…) is the “revolution” I’m wai…
comment
https://natto.dev/ ? https://fermat.ws/ ?
comment
I'm for dissociating the metadata from the files. I have a custom (Text) DB of Artists and Albums, enhanced by online services metadata (last.fm, RYM, Spotify). I'm more interested in flexib…