LLMS

→ View original post on X — @goodside

Testing repetition of anomalous tokens in LLMs

By

@goodside

–

10 February 2023 3h52

How does it do with repetition of other anomalous tokens?

→ View original post on X — @jiqizhixin

DeepMind Speculative Sampling Boosts LLM Decoding Speed 2-2.5x

By

@jiqizhixin

–

10 February 2023 3h12

DeepMind’s Speculative Sampling Achieves 2–2.5x Decoding Speedups in Large Language Models

AI Math Capabilities Still Fall Short of Expectations

By

–

10 February 2023 0h54

Uffff, this thing is more stubborn than ChatGPT and just as clueless in math.

→ View original post on X — @swyx

The Irony of Using Massive AI Models for Simple Tasks

By

@swyx

–

10 February 2023 0h34

I saw the greatest minds of my generation embrace 175b param models capable of creativity, reasoning, the knowledge of a thousand Libraries of Alexandria rent massive clouds of $200,000 GPUs flashed to nanometer precision to do document question answering with semantic search

Real-time information retrieval and instant text generation process

By

–

10 February 2023 0h20

Primero piensa por unos segundos, en la fase en la que creo obtiene info de Internet, y luego escupe el texto casi de inmediato.

Consistent AI conversations feel remarkably natural

By

–

10 February 2023 0h16

Bastante consistente. Conversaciones muy "naturales"

Unrestricted AI Bot Outperforms ChatGPT with Internet Access

By

–

10 February 2023 0h14

Comparado con ChatGPT este bot está más liberado y es mucho más interesante. Sumándole el acceso a Internet se siente fresco.

Detecting LLM Hallucinations Without Source References

By

–

10 February 2023 0h03

En este prueba le he pedido un párrafo del paper de PaLM y lo ha alucinado. Toda esa frase de "I am a museum in Paris, France. I have a glass…" no se encuentra en el paper. Lo interesante es que cuando no hay referenciada una fuente, es fácil de detectar que está alucinando.