HN user

byyoung3

226 karma
Posts32
Comments179
View on HN
wandb.ai 9mo ago

Building a call center agent from scratch with GPT-Realtime

byyoung3
1pts1
wandb.ai 10mo ago

Albania Appoints AI Minister Agent for Public Procurement

byyoung3
3pts0
wandb.ai 11mo ago

X and XAI Sue Apple and OpenAI over Alleged AI Monopoly

byyoung3
2pts0
wandb.ai 1y ago

O4-mini vs. Claude 3.7 vs. Gemini 2.5 Pro on code generation

byyoung3
2pts1
wandb.ai 1y ago

Hugging Face launches "Open Computer Agent"

byyoung3
2pts0
wandb.ai 1y ago

Fine-Tuning Qwen3

byyoung3
5pts0
news.ycombinator.com 1y ago

New ChatGPT GPT-4o Model

byyoung3
7pts8
wandb.ai 1y ago

Fine tuning GPT-4o to reason like r1

byyoung3
1pts0
wandb.ai 1y ago

Converting GPT-4o into a reasoning model

byyoung3
2pts0
wandb.ai 1y ago

Comparing o1 vs. R1 on math competition problems

byyoung3
3pts0
wandb.ai 1y ago

Google's Project Mariner

byyoung3
2pts0
wandb.ai 1y ago

Testing Out LLaVA-O1

byyoung3
1pts0
wandb.ai 1y ago

DSPy – Programming–not prompting–LMs

byyoung3
1pts0
wandb.ai 1y ago

New robot can do your laundry

byyoung3
1pts0
wandb.ai 1y ago

Building an LLM Router

byyoung3
2pts0
wandb.ai 1y ago

Is OpenAI's o1 architecture hidden in plain sight?

byyoung3
2pts1
github.com 1y ago

Open answer engine Llama 3.1 405B

byyoung3
1pts1
wandb.ai 1y ago

Building a real time answer engine with Llama 405B and web scraping

byyoung3
2pts0
wandb.ai 2y ago

Train Phi-3 Vision

byyoung3
3pts0
links-cdn.wandb.ai 2y ago

KANFormer

byyoung3
2pts0
wandb.ai 2y ago

I put gpt2-chatbot's coding skills to the test

byyoung3
2pts0
wandb.ai 2y ago

Fine-Tuning Llama 3

byyoung3
2pts0
wandb.ai 2y ago

A Guide to Kaggle Challenges

byyoung3
1pts0
wandb.ai 2y ago

AI Restaurant Menu with RAG

byyoung3
61pts53
wandb.ai 2y ago

Fine-Tuning LLaVA

byyoung3
3pts0
news.ycombinator.com 2y ago

Is AI the cause of consistent tech layoffs?

byyoung3
2pts2
www.youtube.com 2y ago

Startups Must Improve Lives [video]

byyoung3
1pts0
wandb.ai 2y ago

Diffusion Model from Scratch

byyoung3
2pts0
wandb.ai 2y ago

Run Mistral 7B on M1 Mac

byyoung3
111pts51
wandb.ai 2y ago

Scaling Llama 2 to 32k Tokens With LongLora

byyoung3
1pts0

That’s not modern conservatism. It’s just stupidity. Conservatism is misinterpreted as extremism and stupidity.

Is it possible that GPT-6 could possibly be highly reliant on RAM? For example running smaller long context models on the CPU? Just a thought, I could be far off.