Is Generative AI the next hype cycle of web3?
Generative AI is a platform shift in technology. This powerful new class of large language models makes it possible for machines to write code, draw art and create content with credible and sometimes superhuman results.
A few weeks ago, OpenAi, a nonprofit in which Microsoft is the principal investor (GPT-3 for text, DALL-E2 for images, and Whisper for speech), released Chat GPT-3, which stands out: the model’s performance is a giant leap over GPT-2. It delivers compelling Twitter demos on code generation tasks, snarky joke writing, poetry, and beyond. In the spirit of inquiry, here is a Twitter thread we asked GPT-3 to write for Faculty on how Generative AI can benefit web3:
Web3 is all about decentralization, enabling users to own and control their own data and interactions online.
Generative AI, which uses machine learning to create new content, can help Web3 achieve its goals by enabling users to generate their own content and experiences.
For example, generative AI can be used to create personalized websites and online experiences that are tailored to individual users’ preferences and interests.
This can help make the web more engaging and useful for users, and can also help reduce the amount of centralized control and surveillance on the web.
In addition, generative AI can also be used to create new tools and applications for Web3, such as smart contracts and decentralized autonomous organizations.
These tools can help make the web more secure, transparent, and efficient and can enable new forms of collaboration and value creation.
In short, generative AI has the potential to unlock the full potential of Web3 and help create a more decentralized, user-driven web.
Although generic, it is informative and provides a starting point. AI still needs human interaction and better ‘prompts’ to produce more complex ‘iterations .’Thinking about it as a conversation can vastly improve the output when prompting Chat GPT-3; in many cases, the ‘prompt’ influences the output.
OpenAI admits that GPT “sometimes writes plausible-sounding but incorrect or nonsensical answers”, has input question tweak sensitivity, and exhibits bias behaviour (trainers can influence the output through their inputs). Many believe the technology needs human intervention before being used in business or directly with customers through chatbots.
However, this has not stopped investors and VCs from taking a keen interest in AI start-ups, as the growing hype around “generative AI” is one bright spot in 2022. Generative AI is still in its experimentation phase; however, the freedom to ‘play’ with such powerful AI has already sparked new start-up ideas for creators, investors, and entrepreneurs. It has only taken a couple of years to get from narrow models to code auto-complete. If you apply Moore’s law to generative AI, real innovations are only just beginning.
In a year where investors and VCs have lost so much, investment in Generative AI has increased to $2.1bn, according to PitchBook, even as the broader technology market has declined. Many VCs are looking for the next bandwagon to climb aboard after pivoting away from DeFi. They have capital to deploy and are looking for new opportunities.
Generative AI has the potential to be as transformative as mobile technology but is still at a very early stage in its development. The platform layer is just emerging, and the application space has barely gotten off the ground. These models are good enough today to write the first drafts of blog posts, complete computer code and answer questions (not always accurately!). A wealth of value creation will happen in the near to medium term, and VC investors want to be in on the ground level to reap the rewards of this next-level evolution.