馃摟 (@eddyldn_) header
馃摟 (@eddyldn_) profile picture
Joined June 2012
Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)Photo by 馃摟 (@eddyldn_)
Where is God in this conversation?
This quoted post is unavailable.
410
Man saw a version of his babe on stage that he鈥檚 never witnessed before 馃挃
1
4
1,024
There鈥檚 nothing greater
i鈥檒l never understand the science behind why men love biscuits especially custard creams
1,046
That LinkedIn story has finished me man said fuck it lemme try my luck 馃ぃ馃ぃ馃ぃ
1
7
1,023
Kanye feature confirmed
SKEPTA - GAS ME UP (DILIGENT) JANUARY 26TH 馃毃
1
4
1,756
I still remember seeing this for the first time and noticing the Akira references. Pure cinema man
This Post is from an account that no longer exists. Learn more
1
961
Lol holiday me and London me are not the same person
Spending 3-5k for a holiday to party with the same people from Boxpark is insanity to me
7
1,514
My Spotify wrapped is actually scaring the hoes man
1
1
778
If your Sound Town is Woolwich you鈥檙e not a good person
1
2
789
Nah but what do you mean by that????
2
1
23
2,719
(Ironically) I鈥檓 gonna have to give this to GPT and tell it to ELI5
What is the RLHF that OpenAI鈥檚 secret Q* uses ? So let鈥檚 define this term. RLHF stands for "Reinforcement Learning from Human Feedback." It's a technique used in machine learning where a model, typically an AI, learns from feedback given by humans rather than solely relying on predefined datasets. This method allows the AI to adapt to more complex, nuanced tasks that are difficult to encapsulate with traditional training data. In RLHF AI initially learns from a standard dataset and then its performance is iteratively improved based on human feedbacks. The feedback can come in various forms, such as corrections, rankings of different outputs, or direct instructions. The AI uses this feedback to adjust its algorithms and improve its responses or actions. This approach is particularly useful in domains where defining explicit rules or providing exhaustive examples is challenging, such as natural language processing, complex decision-making tasks, or creative endeavors. This is why Q* was trained on logic and ultimately became adapt at simple arithmetic. It will get better over time, but this is not AGI. This graphic below is an overview and history of RLHF
1
2,260
Nella please I鈥檓 tired of fighting for my life as soon as I step into the office
3
75
25
603
70,370
?
We have reached an agreement in principle for Sam Altman to return to OpenAI as CEO with a new initial board of Bret Taylor (Chair), Larry Summers, and Adam D'Angelo. We are collaborating to figure out the details. Thank you so much for your patience through this.
1
1,335
Spill the ChatGPTea!
Sorry but this ChatGPT saga is juicy I need the tea neooowww. Microsoft is also hella shady for that 馃槀馃槀馃槀
1
1
6
3,893
Binaural beats and Lofi/Jazz is all I even listen to nowadays
This Post is from an account that no longer exists. Learn more
1
2
3
2,064
I hear it tho 馃槀 Not everyday Andrew Huberman sometimes Sam Sulek
2
1,244
Dating down for a snow yeti? She lost twice 馃煝
Hypergamy is real, dont slip fellas u gotta match her energy or she might lose respect for u
1
1
2
1,644