I don’t mean this in a snarky way, but I don’t totally get the value of langchain. I’ve been playing around with it for a few weeks and it still feels like you’re better off using direct APIs (at least for OAI). Am I missing something
June 16, 2023 at 6:00 PM
I don’t mean this in a snarky way, but I don’t totally get the value of langchain. I’ve been playing around with it for a few weeks and it still feels like you’re better off using direct APIs (at least for OAI). Am I missing something
Reposted by 📄🦊
A while back I was walking to get a coffee on my block and saw the sky reflecting on this dolphin blue 1987 Testarossa… feels like just the right amount of mid.
May 25, 2023 at 1:35 PM
A while back I was walking to get a coffee on my block and saw the sky reflecting on this dolphin blue 1987 Testarossa… feels like just the right amount of mid.
This is a compelling argument against the concept of AGI
can ai make crushed ice if not stop talking about it
May 23, 2023 at 5:53 PM
This is a compelling argument against the concept of AGI
Reposted by 📄🦊
The real danger of AI is it’s only a matter of time till a guy at a party introduces himself as a “prompt artist”
May 17, 2023 at 10:45 PM
The real danger of AI is it’s only a matter of time till a guy at a party introduces himself as a “prompt artist”
Reposted by 📄🦊
shitposting is a specific branch of expression that can trace its roots directly to the dadaist, transcendentalist, absurdist, and romantic movements whether you know it or not. shitposters have taken up the banner of Coleridge, Shelley, and Auden in a way as artistically valid as any modern poet.
shitposting is a purpose, and not only that, it is the Great Purpose, the highest synthesis of all the competing and contradictory influences of the world and the cognitive dissonance produced from that conflict are the fuel, and shitposting is the product
What do you identify as ? Are you a shit poster or do you skeet with purpose 🧐
May 16, 2023 at 6:32 PM
shitposting is a specific branch of expression that can trace its roots directly to the dadaist, transcendentalist, absurdist, and romantic movements whether you know it or not. shitposters have taken up the banner of Coleridge, Shelley, and Auden in a way as artistically valid as any modern poet.
One thing I love about research is the level of contention
I have a colleague who read a paper that sent him into such an absolute nerd rage that he’s redirected his research to prove them wrong. Nothing you see coming out of academia is bulletproof.
I have a colleague who read a paper that sent him into such an absolute nerd rage that he’s redirected his research to prove them wrong. Nothing you see coming out of academia is bulletproof.
May 15, 2023 at 3:28 AM
One thing I love about research is the level of contention
I have a colleague who read a paper that sent him into such an absolute nerd rage that he’s redirected his research to prove them wrong. Nothing you see coming out of academia is bulletproof.
I have a colleague who read a paper that sent him into such an absolute nerd rage that he’s redirected his research to prove them wrong. Nothing you see coming out of academia is bulletproof.
Reposted by 📄🦊
LLMs can't do:
1. Causal inference: LLMs can't reason about cause and effect. They can't build models of the world and identify from first principles what interventions can bring change. They can't data mine datasets to make effective recommendations about what data to collect next.
1. Causal inference: LLMs can't reason about cause and effect. They can't build models of the world and identify from first principles what interventions can bring change. They can't data mine datasets to make effective recommendations about what data to collect next.
May 14, 2023 at 8:16 PM
LLMs can't do:
1. Causal inference: LLMs can't reason about cause and effect. They can't build models of the world and identify from first principles what interventions can bring change. They can't data mine datasets to make effective recommendations about what data to collect next.
1. Causal inference: LLMs can't reason about cause and effect. They can't build models of the world and identify from first principles what interventions can bring change. They can't data mine datasets to make effective recommendations about what data to collect next.
Hot take but I don’t think LLMs are the be/end-all solution to all data-related problems
May 14, 2023 at 5:09 PM
Hot take but I don’t think LLMs are the be/end-all solution to all data-related problems
💖
Welcome @paigefox.bsky.social smartest hottest redhead ML engineer I know
May 13, 2023 at 8:49 PM
💖