Viewing profile — rain1
rain1
HN member- Joined
- Tue, May 15, 2018, 8:09 PM UTC
- HN karma
- 1,127
- Public activity
- 180 items
- HN profile
- View on Hacker News ↗
About rain1
No profile information was provided.
Recent public activity
- story
-
comment
Comment #46253724
I've used Google Antigravity to write scripts to download and produce architecture diagrams for various LLMs from huggingface. It's pretty useful so I thought I'd share it. There's…
- story
-
comment
Comment #44444690
The Gemma models are too small to be included in this list. You're right the T5 stuff is very important historically but they're below 11B and I don't have much to say about them. …
-
comment
Comment #44444658
Yes but just purely in terms of entropy, you can't make a model better than GPT-4 by training it on GPT-4 outputs. The limit you would converge towards is GPT-4.
-
comment
Comment #44443289
This is kind of related to the jack morris post https://blog.jxmo.io/p/there-are-no-new-ideas-in-ai-only he discusses how the big leaps in LLMs have mostly come - not so much from …
-
comment
Comment #44443274
It's extremely interesting how powerful a language model is at compression. When you train it to be an assistant model, it's better at compressing assistant transcripts than it is …
-
comment
Comment #44443264
I think that one thing that this chart makes visually very clear is the point I about GPT-3 being such a huge leap, and there being a long gap before anybody was able to match it.
-
comment
Comment #44443241
This is really awesome. Thank you for creating that. I included a screenshot and link to the chart with credit to you in a comment to my post.
-
comment
Comment #44442808
I can correct mistakes. > it somehow merged Llama 4 Maverick's custom Arena chatbot version with Behemoth I can clarify this part. I wrote 'There was a scandal as facebook decided …
-
comment
Comment #44442612
I have corrected that. It was supposed to say "None of this document was written by AI." Thank you for spotting the error.
- story
- story
-
comment
Comment #41463926
> Take care of your mental health How?
-
comment
Comment #40112534
todsacerdoti is a spambot btw
- story
-
comment
Comment #37272487
I don't understand this. Please can you point me to information about it?
-
comment
Comment #37272479
The people that are astonished by this just need to learn why. It's not the function that is wrong, it's those people.
-
comment
Comment #36736793
This is incorrect, the goats and car are behind doors. They are not inside cardboard boxes.
-
comment
Comment #36685467
This is an example of hallucination. An LLM doesn't know anything about itself - it can be pre-prompted with facts about itself, but this is going to be an example of it just makin…
-
comment
Comment #36136066
tell me you're posting from an armchair without telling me you're posting from an armchair
- story
-
comment
Comment #36101746
what the actual fuck were they thinking uploading dolphin to steam??
-
comment
Comment #36092920
Why don't they let us edit what the bot says? Could be useful.
-
comment
Comment #36031625
This is the future of linux syscalls. Get on board with this or get left behind.