Notes tagged with "ai": Nonlinear Function

69 notes tagged with "ai"

AI is just tech

Most 'AI' in business domains doesn't have any intellectual relationship to AGI research. In the vast majority of problem spaces, what you…

Tagged with: #ai

AI predictions

In the spirit of [ prediction as a model-building exercise ]. Language modeling: system writes publishable poetry: debatably already…

Tagged with: #ai#machine-learning

AI for math

Doing [ math ] seems like a really promising area for AI. And by 'math' I mean math research (not arithmetic, which computers are already…

Tagged with: #ai#math#ideas

AI research landscape

As of April 2021: Giant [ transformer ]s work better than anyone has a right to expect. GPT3 is fucking amazing. [ DALL-E ] clearly has some…

Tagged with: #ai

AI safety

AI safety, as a term, is sterile and hard to get excited about. Preventing catastrophe is important, but doesn't motivate me, since [ the…

Tagged with: #ai#morality#alignment

GPT

Tagged with: #ai#transformers

Minerva

Minerva : they basically fine-tuned a language model on ArXiv papers and web pages containing LaTeX, so that it can produce latex. This is…

Tagged with: #ai

Tesla Autopilot

On the Robot Brains podcast , Andrej Karpathy explained to Pieter Abbeel why he thinks Tesla has the right approach to self-driving. Tesla…

Tagged with: #ai

abstraction

Abstraction is lossy [ compression ]. A good abstraction throws away everything not relevant to a particular problem, while preserving a…

Tagged with: #ai#how-to-think

agency

see also [ agent ]

Tagged with: #ai#psychology

agency and confidence

There is a similarity in kind between the negative effects of: rape slavery feeling forced to work on someone else's projects, by a boss…

Tagged with: #ai#psychology

agent

see also [ agency ]

Tagged with: #ai#modeling

artificial intelligence

Intelligence is what makes humans special. PhdAdvisor defines it as the ability to make high-quality decisions. I think we can distinguish…

Tagged with: #ai

attention

One of the best ideas in machine learning. (I even thought so in 2011!) There are two common mechanisms: 'soft' and 'hard'. In both cases…

Tagged with: #machine-learning#ai#meditation#psychology#neuroscience

bitter lesson

http://www.incompleteideas.net/IncIdeas/BitterLesson.html The bitter lesson is based on the historical observations that 1) AI researchers…

Tagged with: #ai

capabilities research

In the discourse around [ AI safety ] you sometimes see the claim that research on AI capabilities is harmful to the extent that it outpaces…

Tagged with: #ai

computation is important

Arguably the core insight of deep learning / [ differentiable program ]ming is that the shape and structure of the computations we do are so…

Tagged with: #machine-learning#ai

computational life coach

How do you start building and selling [ computational therapy ]? It can't just be a medical product, because that's a hugely regulated and…

Tagged with: #ideas#ai

computational therapy

See also: [ computational life coach ] A recurring dream I have is to use AI to solve mental health. It is simultaneously one of the most…

Tagged with: #ideas#ai

consciousness

Philosophical views on consciousness: Buddhist and meditative traditions focus on [ awareness ]. They claim that consciousness has nothing…

Tagged with: #meditation#ai

conversation as a game

Okay so there’s a lot of research on what conversations are, what the goals are (of course I don’t know most of this research…). It seems as…

Tagged with: #ai#how-to-think

decision transformer

paper: Chen, Lu, et al. 2021, https://arxiv.org/abs/2106.01345 Trajectories are represented as sequences: where is the return-to-go, i.e…

Tagged with: #ai#reinforcement-learning#papers

deep RL notes

Notes from John Schulman's Berkeley course on deep [ reinforcement learning ], Spring 2016. Value vs Policy-based learning Value-based…

Tagged with: #machine-learning#ai#reinforcement-learning

differentiable environments

Maybe a stupid idea, but I wonder if the idea behind differentiable physics simulators (like Brax) can be extended more broadly to rich…

Tagged with: #reinforcement-learning#ai

direct preference optimization

References: Direct Preference Optimization: Your Language Model is Secretly a Reward Model This seems like a compelling reframing of…

Tagged with: #ai#reinforcement-learning

emergent capabilities

A consequence of [ phase transition ]s in [ large models ] is that models may end up having capabilities we didn't expect. For example…

Tagged with: #ai

embedded agent

Notes on Abram Demski and Scott Garrabrant's sequence on Embedded Agency Embedded Agents : Classic models of rational [ agency ], such as…

Tagged with: #alignment#ai#buddhism

explicit models of uncertainty

(note: this is dancing around the issues around why I think [ probabilistic programming is not AI research ], even if it will be a…

Tagged with: #ai#bayes

fast weights

On an evolutionary timescale, it's useful to evolve structures that can learn quickly. The nervous system is an evolved organ system for…

Tagged with: #ai#machine-learning

general intelligence

Is there such a thing as 'general intelligence'? What capabilities does it require? Is it a goal worth striving for? We usually speak about…

Tagged with: #ai

general techniques are simple

If you need to open a specific lock, you can use a key that encodes the precise information needed to open that lock. If you need to open…

Tagged with: #ai

generalized policy iteration

Sutton and Barto use this as a general term for any form of interleaving policy evaluation steps with policy improvement steps. This…

Tagged with: #ai#machine-learning

glimpses of AI

An intelligent [ agent ] should work to understand the world. This understanding takes the form of a set of relevant [ abstraction ]s, a…

Tagged with: #ai

grounded

A nice observation from Percy Liang on the relationship between language modeling and grounded understanding: Just because you don't…

Tagged with: #ai#machine-learning

high-level actions

The plans I make now include components that would have been impossible for me to conceive of as a kid. At the moment (July 2020), I'm…

Tagged with: #ai

in silico

In the 21st century, humanity is developing a new form of engineering. Rather than manually designing artifacts, we are optimizing over…

Tagged with: #ai

instrumental goal

To achieve final goals, we have to break them down into a hierarchy of instrumental goals, and then get to work on achieving those. And for…

Tagged with: #ai#how-to-think

intelligence is not consciousness

A lot of discussion around [ artificial intelligence ] implicitly conflates intelligence with [ consciousness ]. It assumes that as we…

Tagged with: #ai#morality#how-to-think#meditation

intelligence forklift

Boaz Barak writes in GPT as an "Intelligence Forklift." that [ language model ]s seem to function effectively as [ tool AI ] that can…

Tagged with: #ai

large control policies

Taco Cohen speculates on Large Control Policies as a successor to large language models: https://twitter.com/TacoCohen/status…

Tagged with: #ai

love is value alignment

What does it mean to love someone? Of course this question has as many answers as there are people, and probably more. But here's one view…

Tagged with: #ai#alignment#relationships

many models

An idea I got from [ John Higgs ]'s discussion of metamodernism is that taking [ all models are wrong ] to its logical conclusion requires…

Tagged with: #modeling#ai#how-to-think

mesa optimizer

References: Risks from Learned Optimization in Advanced Machine Learning Systems A [ reinforcement learning ] algorithm attempts to find the…

Tagged with: #ai#reinforcement-learning

meta-reasoning

Stuart Russell told the story of giving a talk on meta-reasoning at Stanford, with Don Knuth in the audience, where he opened with a slide…

Tagged with: #ai

monte carlo tree search

A very natural form of [ meta-reasoning ] that selects the most promising computations. The simplest form of 'expanding' a node assumes a…

Tagged with: #ai

multiplicative interaction

From a conversation I had about [ attention ] mechanisms in deep architectures. Maybe that terminology is too suggestive --- it's just a…

Tagged with: #ai#machine-learning

objectives are big

A very incomplete and maybe nonsensical intuition I want to explore. Classically, people talk about very simple [ reward ] functions like…

Tagged with: #ai#reinforcement-learning#alignment

ontological crisis

How do we maintain values when our models of the world shift? If someone's goal in life is to "do God's will", and then they come to believe…

Tagged with: #alignment#ai

perceiver

reading the perceiver papers from Deepmind: Perceiver: Jaegle et al 2021 https://arxiv.org/abs/2103.03206 Perceiver-IO: Jaegle et al 202…

Tagged with: #ai#machine-learning

personal AI Effect

The AI Effect refers to the widely-recognized phenomenon that 'once we know how to do it, it's not AI'. For example, playing chess well…

Tagged with: #ai

positional embedding

There are a few ways to do this. Google's PaLM uses rotary embeddings so it seems like that's probably close to the state of the art? But…

Tagged with: #transformers#ai

predictive agent

Consider an agent that is purely concerned with [ predictive processing ]: finding the optimal [ compression ], or equivalently the optimal…

Tagged with: #ai

priors are conceptual attention

A Bayesian view of (one aspect of) [ attention ] inspired by a conversation with Shamil Chandaria on [ predictive processing ]. (but this…

Tagged with: #ai

probabilistic program induction

Can we think about [ generative flow network ]s as a potentially tractable formulation of probabilistic program induction?! executing a line…

Tagged with: #machine-learning#ai

reinforcement learning

Note : see [ reinforcement learning notation ] for a guide to the notation I'm attempting to use through my RL notes. Three paradigmatic…

Tagged with: #ai#machine-learning#reinforcement-learning

researchers don't always know best

People who do research have a very ground-level, zoomed-in view of their field. They know where the current obstacles are, how incredibly…

Tagged with: #ai#research

reward is enough

Silver, Singh, Precup, and Sutton argue that Reward is enough : maximizing a reward signal implies, on its own, a very broad range of…

Tagged with: #ai#reinforcement-learning

reward

stray thoughts about reward functions (probably related to the [ agent ] abstraction and the [ intentional stance ]) one can make a…

Tagged with: #ai#reinforcment-learning#alignment

simulator AI

References: https://generative.ink/posts/simulators/ It seems pretty clear that the intelligence emerging from [ language model ]s is not…

Tagged with: #ai

steering language models

Getting language models to align their output with human preferences would be highly useful for [ computational life coach ]ing. What's the…

Tagged with: #ai

theory of intelligence

tl;dr : the ideas we need to build intelligent systems may be different from those we need to understand them. Both are important, but…

Tagged with: #ai#how-to-think

thoughts are actions

The [ agent ] model of intelligence imposes a sharp distinction between the agent and its environment, where the agent 'chooses' actions…

Tagged with: #ai#how-to-think

tool AI

Sometimes mentioned as a potential approach to [ AI safety ]. Gwern: Why Tool AIs want to be Agent AIs (roughly: because treating…

Tagged with: #ai

training for consistency

These days we think a lot about using data to train large [ language model ]s. But there's only so much data in the world; eventually we'll…

Tagged with: #ai#machine-learning#how-to-think

transformer

The core of the transformer architecture is multi-headed [ attention ]. The transformer block consists of a multi-headed attention layer…

Tagged with: #ai#machine-learning#transformers

transformers with memory

Incorporating explicit memory and retrieval seems pretty clearly like the next frontier in language modeling and AI more broadly. We have…

Tagged with: #ai

worldly objective

This may be a central point of confusion: how do we define AI systems that have preferences about the real world , so that their goals and…

Tagged with: #alignment#ai#buddhism

wrong models in AI

The models we use in AI are [ all models are wrong|wrong ] (if maybe still useful). How? Agency The [ agent ] model assumes a separation of…

Tagged with: #ai

AI reflections master

This page is a general jumping-off point for organizing my thoughts about the [ AI research landscape ], where the field is, where it is…

Tagged with: #ai

See All tags