Live data from Hacker News

Viewing profile — enricoros

enricoros

HN member
Joined
Sun, Mar 19, 2023, 9:55 AM UTC
HN karma
49
Public activity
19 items

About enricoros

No profile information was provided.

Recent public activity

  1. comment
    Comment #46787609

    CCP-bench has gotten WAY better on K2.5! https://big-agi.com/static/kimi-k2.5-less-censored.jpg

  2. comment
    Comment #46786159

    Same ask, same session, side by side, no system prompt. K2 Preview refuses, K2.5 gives factual history. Frankly surprising and welcome to see loosening CCP-sensitive topics between…

  3. story
  4. story
    Show HN: Big-AGI 2 – Spent a year obsessing over AI for thinking

    Hey HN, Enrico here. Some of you might remember Big-AGI from early chat days. The response here pushed me to quit my job and go all-in. Spent the last year rebuilding it properly (…

  5. comment
    Comment #39902062

    One person on Discord has called this 'taking the idea of self-consistency forward to ensemble model usage'. I guess this is, technically, what this approach is about :)

  6. comment
    Comment #39902035

    Thank you so much - there's much more and much better coming ;)

  7. comment
    Comment #39900951

    Yes, the only issue is the usage of tokens, which is obviously greater as we are sampling more of the solutions space. But it's a compromise to have GPT-4.5 level intelligence with…

  8. comment
    Comment #39900473

    Same experience. Once you beam you look for it everywhere!

  9. comment
    Comment #39900470

    Same. I like using Opus | Gpt-4 | Gemini Pro (I don't have Ultra) | Mistral Large.

  10. comment
    Comment #39900464

    There's a combo box on the right side, and when you click on the "Add Merge" (green) button, the currently active model will be selected.

  11. story
    Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning

    HN, first things first: one year ago you make me believe in my opensource AI project, and I'm forever grateful[1]. I am back with Beam - a technique to use diverse LLMs to generate…

  12. comment
    Comment #35445732

    TL;DR & DIY: asked gpt-4 this prompt "Cluster the top10 categories of complaints by the users, and describe each category with a few adjectives/nouns in order or importance." as of…

  13. comment
    Comment #35286589

    Very interesting to follow the chain on the console. Vry good in breaking down multi-part questions, way better than Google Assistant - and then uses G to search. Thx for showing t…

  14. comment
    Comment #35229344

    Very good point. Once you start breaking down a llm into presets/delegators, you introduce basically if-else, with all the problems of that split. Lack of visibility, local vs glob…

  15. comment
    Comment #35229277

    When the user selects one of those, any query will reveal the prompt. Can be changed but the change won't be persisted yet. We added a 'Custom' preset today that requires editing. …

  16. comment
    Comment #35229259

    OP: I went to sleep with this as my 1st post and 1 star, and woke up with a PR for 3.5-Turbo pending. Community for the win!

  17. comment
    Comment #35229253

    Hey guys, op here. Merged the PR for 3.5-Turbo support and cleaned up the code (very good observations on all the places 'gpt-4' was hardcoded). Combo box to select the model. GPT-…

  18. comment
    Comment #35217537

    What does it take to make a basic ChatGPT-like frontend, with code highlighting, run in sandbox, drop-files, and 'acting' in prompts? Clone away and enjoy. First time poster

  19. story