We're starting to roll out API support for Gemini 1.5 Pro for developers. We're excited to see what you build with the 1M token context window!

We'll be onboarding people to the API slowly at first, and then we'll ramp it up. In the meantime, developers can try out Gemini 1.5…

Gemini 1.5 Pro - A highly capable multimodal model with a 10M token context length

Today we are releasing the first demonstrations of the capabilities of the Gemini 1.5 series, with the Gemini 1.5 Pro model. One of the key differentiators of this model is its incredibly long…

LLMs like ChatGPT are an amazingly powerful breakthrough in AI and a transformative general purpose technology, like electricity or the internet. LLMs will reshape work and our lives this decade. They are not just a blurry photocopier or an extruder of meaningless word sequences.

Can we make RAG applications more robust with fine-tuning? A paper by Microsoft and UC Berkley put this to the test to see if small open LLMs, like AI at Meta Llama 7B, can match OpenAI GPT-3.5.
They called it “Retrieval Augmented Fine Tuning (RAFT)”, where you train an LLM…

Trust in the law of cumulative returns.

The power of actively practicing a language 10 Minutes per day results in great outcomes.

I’ve been doing this with DuoLingo for Japanese since 2019. Here are the outcomes. #japanese #Duolingo #日本語

I think AI agentic workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models. This is an important trend, and I urge everyone who works in AI to pay attention to it.

Today, we mostly use LLMs in zero-shot mode, prompting…

huggingface.co/blog/phi2-inte…

run inference on a mid-range laptop powered by an Intel Meteor Lake CPU.

Phi-2 on Intel Meteor Lake

“Nosce te ipsum”
(Know thyself)

There is clearly a magical power & big wisdom in some words.

This is a a beautiful compilation of Latin “Sententia” from a Linguistics Professor Çiğdem Dürüşken in Turkish.

“Seven Failure Points When Engineering a Retrieval Augmented Generation System” arxiv.org/pdf/2401.05856…

towardsdatascience.com/12-rag-pain-po… 12 RAG Pain Points and Proposed Solutions

arxiv.org/pdf/2401.12599… Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition

“If you can’t say no, then your yes’s mean nothing.“

POLYMATH

noun

a person of wide knowledge or learning.'a Renaissance polymath'

“Peter Thiel believes talented people are not specialists.

Rather, they're almost always polymaths because they're naturally curious.

Curious about businesses, politics, science, history, poetry...or anything that impacts us as humans.”

Finished 1 day after watching Dune: Part II

The Era of 1-bit LLMs:
All Large Language Models are in 1.58 Bits

- significantly more cost-effective in terms of latency, memory, throughput, and energy consumption

- defines a new scaling law and recipe for training: 13B BitNet b1.58 is more efficient, than 3B FP16 LLM.

👏