from Hacker News

profsummergig

joined 6/6/19, 4:23 PM has 595 karma

• How would I go about finetuning Deep Seek or Llama to do this?

  by profsummergig on 3/15/25, 12:12 AM, with 0 comments

• Best explanation of Q, K, V? (Attention)

  by profsummergig on 2/24/25, 6:35 PM, with 2 comments

• How are founders finetuning AI with limited resources?

  by profsummergig on 2/23/25, 3:34 AM, with 2 comments

• Consortium for Elections and Political Process Strengthening(USAID $486M)

  by profsummergig on 2/19/25, 2:25 PM, with 0 comments

• How is the Herculean task of human supervision in LLM pre-training conducted?

  by profsummergig on 2/17/25, 5:26 PM, with 0 comments

• India's AI Vaporware

  by profsummergig on 2/14/25, 7:34 AM, with 1 comments

• Ask HN: What do you read to keep up with AI?

  by profsummergig on 1/23/25, 12:33 AM, with 12 comments

• Ask HN: How to try out AIML finetuning on a laptop?

  by profsummergig on 1/20/25, 7:30 PM, with 3 comments