Below are articles that I’m reading, that I thought you might be interested in too.
I've been doing emotional work like extended meditation retreats, Internal Family Systems (IFS), Ideal Parent Figures (IPF), Focusing, etc., for a long time, but self-administered EMDR has actually been one of the most helpful techniques of them all to me!
Each LLM call/generation can be thought of as trying to perform a single computational task – one Natural Language OPeration (NLOP).
Part 2 discusses how to compose multiple tasks with control flows (e.g. if statement, for loop) and incorporate tools (e.g. SQL executor, bash, web browsers, third-party APIs) for more complex and powerful applications.
Download a PDF of the paper titled RWKV: Reinventing RNNs for the Transformer Era, by Bo Peng and 29 other authors
So when Abi alerted me on how he has teamed up with the lead researchers behind DORA and SPACE to publish a new framework which they describe as a “developer-centric approach to developer productivity,” it piqued my curiosity:
In the next prompt section, AutoGPT provides performance evaluation guidelines for OpenAI.
The base model is then finetuned with an instruction dataset, and the purpose of this is to teach it to be helpful, to obey the user, answer questions, and engage in conversation.
And I still wouldn’t rule out 100 years – it’s just that my confidence that this wasn’t coming for quite a while has been shaken by the realisation that biological intelligence and digital intelligence are very different, and digital intelligence is probably much better.”
The bottom line of the thesis presented here is that there may be a path to build immensely useful AI systems that completely avoid the issue of AI alignment, which I call AI scientists because they are modeled after ideal scientists and do not act autonomously in the real world, only focusing on theory building and question answering.
When a LinkedIn member updates their profile, the request is sent to the Profile backend application which serializes the change by converting the document into an Avro binary format before persisting it in Espresso.
In ChatGPT Prompt Engineering for Developers, you will learn how to use a large language model (LLM) to quickly build new and powerful applications.
Through numerous experiments, his team proved that the subconscious mind stores information that influences people’s decision making, without them being aware of it.
This API allows you to create sophisticated conversational interfaces that use a variety of Tools (e.g. Google Search, Calculator) to answer questions.
The Text-to-Mel Spectrogram Encoder is an important component of real-time voice cloning systems, as it allows the system to generate the Mel-scale spectrograms that are used as input to the Vocoder to synthesize the target speaker’s voice.
What has happened is that a number of GPT-4 systems, from both OpenAI and Microsoft, have been given the ability to use tools, with dramatic effects on their abilities, and their relevance to real-world tasks.
The increased attention on AI (and making AI good) means that many more people will find their way to our communities, and recruiting will be much easier (it already is compared to a few years ago, as far as I can tell).
Besides eliminating this depth/breadth tradeoff, I think an underrated aspect of interactive learning with GPT is that you're forced to ask questions explicitly, instead of just clicking around blindly on the web.
The platform has been effective in making money off its augmented reality features, drawing a swarm of marketers looking to provide customers with an immersive ad experience.