Viewing profile — albystein
albystein
HN member- Joined
- Wed, Nov 13, 2019, 2:02 AM UTC
- HN karma
- 11
- Public activity
- 18 items
- HN profile
- View on Hacker News ↗
About albystein
No profile information was provided.
Recent public activity
-
comment
Comment #44608953
Hi Peter, Thanks for hosting this AMA. I’ve an immigration issue related to status transition. So I came to the U.S on an F-1 visa about 6 years ago. However, during the course of …
-
comment
Comment #43162385
Just increased message limits to 100 per day
-
story
Show HN: Free AI Mobile App Generator
Hi HN About three weeks ago, I was playing around with the popular app generation tools, but at the time, none of the major platforms supported mobile app gen. So I thought it woul…
-
comment
Comment #37007305
this seems like a plausible outcome, and if true could spell disaster for OpenAI models relative to the competition and open source models. Currently, reliability is one of the cor…
-
comment
Comment #37007226
this hypothesis makes a lot of sense. if indeed gpt-4 is a sparse MoE—which i believe it is—then OpenAI must have tested and proved their initial idea of a large capacity MoE LLM m…
-
comment
Comment #35138827
I think hallucination is akin to encountering a problem on a test to which you don’t fully remember the right concept to solve it. You might attempt the problem with whatever littl…
- comment
-
comment
Comment #35138630
I think it depends on the sampling/decoding method. Also, perhaps you could elaborate more on what you mean by top_p
-
comment
Comment #35138520
this is not what language models typically output as logits though. perhaps the term now is being misused and it’s causing a lot of confusion
-
comment
Comment #35138470
Basically, logits are the raw outputs of the last linear layer of a neural network just before the softmax(for multi-class classification tasks) or the sigmoid(for binary classific…
-
comment
Comment #35138011
This is exactly how I understand it. Although, I feel the thermodynamics analogy might be more intuitive to most people
-
comment
Comment #35137952
I’m not sure if comparing it to the greedy algorithm is the correct way to think about it. Even after applying the temperature, if you use greedy decoding, you’ll still pick the ou…
-
comment
Comment #34857907
Typically, in new markets and product categories, you should not consider early complimentary products as competitors, but rather as partners. During these early days, all particip…
-
comment
Comment #34733225
I think this line of reasoning is misguided. What’s striking and more important to focus on are the abstract reasoning abilities of these systems. Language, as you mentioned, abstr…
-
comment
Comment #33935304
This a very well put comment with a great analogy. A new emerging paradigm of action-driven LLMs is taking the approach of using the reasoning abilities of LLMs to drive agents tha…
-
comment
Comment #33935093
The problem of hallucination in LLMs is a well-known and studied problem and solutions have been proposed to counter it. The most promising one is augmenting LLMs with a retrieval …
-
comment
Comment #24122293
Alchemy API is a suite of developer tools that powers 70% of the top ethereum DApps and projects like CrytoKitties, Compound, MakeDAO, Aave, Dharma, etc. They just officially opene…
- story