Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
← Înapoi la Urmăritori

Adam Bronte

adam.bronte.me/feed/?type=rss
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 8

  1. Benchmarking LLMs using Wordle

    (Adam Bronte)

    LLM benchmarks are sort of an odd thing.

  2. Building your own RAG

    (Adam Bronte)

    I like to read and I read a good amount.

  3. Dogfooding your product is not enough

    (Adam Bronte)

    You should use the product you are building, yes?

  4. How different LLMs write "Hello World"

    (Adam Bronte)

    Whenever I'm trying out a new LLM, my go to prompt is always Write a hello world program in python.

  5. Using LLMs for factual dataset generation

    (Adam Bronte)

    When building Fresh Tracks I needed to put together a dataset of a bunch of ski resorts and some information around them.

  6. LLMs are designed to hallucinate

    (Adam Bronte)

    Hallucination in the LLM world simply means the model made a bad prediction.

  7. Using Kamal do deploy a python background job

    (Adam Bronte)

    With Kamal 2.0 the ability to deploy non-ruby and non-rails apps was added.

  8. Can you poison popular LLM training data?

    (Adam Bronte)

    A while back some colleagues and I were talking about what if you could flood the internet with specific content, could you influence today's popular LLMs?