But the ruliad took things to another level. For now I could see that the very laws of physics we know were determined by the way we are as observers. I’d always imagined that the laws of physics just are the way they are. But now I realized that we could potentially derive them from the inevitable structure of the ruliad, and very basic features of what we’re like as observers.

Our Physics Project is based on the idea of applying rules to abstract hypergraphs that represent space and everything in it. But given a particular rule, there are in general many ways it can be applied. And a key idea in our Physics Project is that somehow it’s always applied in all these ways—leading to many separate threads of history, that branch and merge—and, importantly, giving us a way to understand quantum mechanics.

And so it was, soon after my birthday in 2019, that we embarked on our Physics Project. It was a mixture of computer experiments and big concepts. But before the end of 2019 it was clear: it was going to work! It was an amazing experience. Thing after thing in physics that had always been mysterious I suddenly understood. And it was beautiful—a theory of such strength built on a structure of such incredible simplicity and elegance.

A major theme of my work since the early 1980s had been exploring the consequences of simple computational rules. And I had found the surprising result that even extremely simple rules could lead to immensely complex behavior. So what about the universe? Could it be that at a fundamental level our whole universe is just following some simple computational rule?

I’ve spent my life alternating between technology and basic science, progressively building a taller and taller tower of practical capabilities and intellectual concepts (and sharing what I’ve done with the world). Five years ago everything was going well, and making steady progress. But then there were the questions I never got to. Over the years I’d come up with a certain number of big questions. And some of them, within a few years, I’d answered. But others I never managed to get around to.

Empirical idealism, as Kant here characterizes it, is the view that all we know immediately (non-inferentially) is the existence of our own minds and our temporally ordered mental states, while we can only infer the existence of objects “outside” us in space. Since the inference from a known effect to an unknown cause is always uncertain, the empirical idealist concludes we cannot know that objects exist outside us in space.

After 1836 Chaadayev continued to write articles on cultural and political issues "for the desk drawer." Chaadayev defies categorization; he was not a typical Russian Westernizer due to his idiosyncratic interest in religion; nor was he a Slavophile, even though he offered a possible messianic role for Russia in the future. He had no direct followers, aside from his "nephew" and amanuensis, Mikhail Zhikharev, who scrupulously preserved Chaadayev's manuscripts and tried to get some of them published after Chaadayev's death. Chaadayev's lasting heritage was to remind Russian intellectuals to evaluate any of Russia's supposed cultural achievements in comparison with those of the West.

This illustration shows four alternative ways to nudge an LLM to produce relevant responses:Generic LLM - Use an off-the-shelf model with a basic prompt. The results can be highly variable, as you can experience when e.g. asking ChatGPT about niche topics. This is not surprising, because the model hasn’t been exposed to relevant data besides the small prompt.Prompt engineering - Spend time structuring the prompt so that it packs more information about the desired topic, tone, and structure of the response. If you do this carefully, you can nudge the responses to be more relevant, but this can be quite tedious, and the amount of relevant data input to the model is limited.Instruction-tuned LLM - Continue training the model with your own data, as described in our previous article. You can expose the model to arbitrary amounts of query-response pairs that help steer the model to more relevant responses. A downside is that training requires a few hours of GPU computation, as well as a custom dataset.Fully custom LLM - train an LLM from scratch. In this case, the LLM can be exposed to only relevant data, so the responses can be arbitrarily relevant. However, training an LLM from scratch takes an enormous amount of compute power and a huge dataset, making this approach practically infeasible for most use cases today.

Macaulay claimed that his memory was good enough to enable him to write out the whole of Paradise Lost. But when preparing his History of England, he made extensive notes in a multitude of pocketbooks of every shape and colour.

Vector databases are used to retrieve relevant documents using similarity search. Vector databases can be standalone or embedded with the LLM application (e.g., Chroma embedded vector database). When structured (tabular) data is needed, an operational data store, such as a feature store, is typically used. Popular vector databases and feature stores are Weaviate and Hopsworks that both provide time-unlimited free tiers.

RAG LLMs can outperform LLMs without retrieval by a large margin with much fewer parameters, and they can update their knowledge by replacing their retrieval corpora, and provide citations for users to easily verify and evaluate the predictions.

With the embedding API, you can apply the innovation of embeddings, combined with the LLM capability, to various text processing tasks, such as:LLM-enabled Semantic Search: text embeddings can be used to represent both the meaning and intent of a user's query and documents in the embedding space. Documents that have similar meaning to the user's query intent will be found fast with vector search technology. The model is capable of generating text embeddings that capture the subtle nuances of each sentence and paragraphs in the document.LLM-enabled Text Classification: LLM text embeddings can be used for text classification with a deep understanding of different contexts without any training or fine-tuning (so-called zero-shot learning). This wasn't possible with the past language models without task-specific training.LLM-enabled Recommendation: The text embedding can be used for recommendation systems as a strong feature for training recommendation models such as Two-Tower model. The model learns the relationship between the query and candidate embeddings, resulting in next-gen user experience with semantic product recommendation.LLM-enabled Clustering, Anomaly Detection, Sentiment Analysis, and more, can be also handled with the LLM-level deep semantics understanding.

Grounded to business facts: In this demo, we didn't try having the LLM to memorize the 8 million items with complex and lengthy prompt engineering. Instead, we attached the Stack Overflow dataset to the model as an external memory using vector search, and used no prompt engineering. This means, the outputs are all directly "grounded" (connected) to the business facts, not the artificial output from the LLM. So the demo is ready to be served today as a production service with mission critical business responsibility. It does not suffer from the limitation of LLM memory or unexpected behaviors of LLMs such as the hallucinations.

In the new AI model, you ingest the data in real time, apply your models by reaching to one or multiple GPT services and action on the data while your users are in the online experience. These GPT models may be used for recommendation, classification personalization, etc., services on real-time data. Recent developments, such as LangChain and AutoGPT, may further disrupt how modern applications are deployed and delivered.

Let’s say, for example, you search for a very specific product on a retailer’s website, and the product is not available. An additional API call to an LLM with your request that returned zero results may result in a list of similar products. This is an example of a vector search, which is also known as a similarity or semantic search.

Conventional search works on keys. However, when the ask is a natural query, that sentence needs to be converted into a structure so that it can be compared with words that have similar representation. This structure is called an embedding. An embedding uses vectors that assign coordinates into a graph of numbers — like an array. An embedding is high dimensional as it uses many vectors to perform semantic search.

followers of Spinoza adopted his definition of ultimate substance as that which can exist and can be conceived only by itself. According to the first principle of his system of pantheistic idealism, God (or Nature or Substance) is the ultimate reality given in human experience.

Historically, answers to this question have fallen between two extremes. On the one hand is the skepticism of the 18th-century empiricist David Hume, who held that the ultimate reality given in experience is the moment-by-moment flow of events in the consciousness of each individual. That concept compresses all of reality into a solipsistic specious present—the momentary sense experience of one isolated percipient.

two basic forms of idealism are metaphysical idealism, which asserts the ideality of reality, and epistemological idealism, which holds that in the knowledge process the mind can grasp only the psychic or that its objects are conditioned by their perceptibility.

idealism, in philosophy, any view that stresses the central role of the ideal or the spiritual in the interpretation of experience. It may hold that the world or reality exists essentially as spirit or consciousness, that abstractions and laws are more fundamental in reality than sensory things, or, at least, that whatever exists is known in dimensions that are chiefly mental—through and as ideas.

it is this architecture, the one which is in the heads of those writing the code, that is the most important. In adopting this decentralised approach, where the practice of architectural decision-making is much more dispersed, this problem is in many ways, mitigated

For example, productivity and satisfaction are correlated, and it is possible that satisfaction could serve as a leading indicator for productivity; a decline in satisfaction and engagement could signal upcoming burnout and reduced productivity.

• Design and coding. Volume or count of design documents and specs, work items, pull requests, commits, and code reviews. • Continuous integration and deployment. Count of build, test, deployment/release, and infrastructure utilization. • Operational activity. Count or volume of incidents/issues and distribution based on their severities, on-call participation, and incident mitigation.

The SPACE framework provides a way to logically and systematically think about productivity in a much bigger space and to carefully choose balanced metrics linked to goals—and how they may be limited if used alone or in the wrong context.

the brain evolved to be uncertainty-averse. When things become less predictable — and therefore less controllable — we experience a strong state of threat. You may already know that threat leads to “fight, freeze, or flight” responses in the brain. You may not know that it also leads to decreases in motivation, focus, agility, cooperative behavior, self-control, sense of purpose and meaning, and overall well-being. In addition, threat creates significant impairments in your working memory: You can’t hold as many ideas in your mind to solve problems, nor can you pull as much information from your long-term memory when you need it.

Metrics shape behavior, so by adding and valuing just two metrics, you've helped shape a change in your team and organization. This is why it's so important to be sure to pull from multiple dimensions of the framework: it will lead to much better outcomes at both the team and system levels.

The framework is meant to help individuals, teams, and organizations identify pertinent metrics that present a holistic picture of productivity; this will lead to more thoughtful discussions about productivity and to the design of more impactful solutions

Having too many metrics may also lead to confusion and lower motivation; not all dimensions need to be included for the framework to be helpful.

The fact that a team's need for a decision to be taken can be met by themselves also leads to appropriate levels of bias-to-action, with accountability acting as a brake when it's required.