Other Copilots exist. Millions of users, > 500k students, teachers, open source maintainers Started as ‘code completion’ product Developers writing code ~55%† faster People feel more ful fi lled (~75%†), con fi dent in code quality (~85%†), more focused VS Code, VS, Neovim, JetBrains, GitHub.com Technical Preview June 2021, ‘generally available’ June 2022. https://gh.io/accenture † With the vast majority of it being retained. Maintaining ‘ fl ow’ state.
you are likely using it There is a “there” there Moore’s law will continue to hold People are going try all sorts of crazy sh*t A community of enablers should have opinions Some working assumptions… Whether it’s ChatGPT or GitHub Copilot, these are technologies people are using. Generative AI can be genuinely useful when applied to the right problems. Models will likely become more capable, costs will reduce, more will be possible for less. Just check your favourite tech news site. And that’s what I’m sharing with you today.
They are changing how people work There will be much more code in the future Lots of tools (and models) to experiment with There’s real work to do to build responsibly Some working assumptions… Answer questions, summarise content, generate code, understand sentiment. Cost of exploring an idea is trending towards zero. Including written by many people who currently aren’t (lower barrier to entry). Open AI, AWS Bedrock, Hugging Face, Replicate. Please learn about responsible AI development. rai.ac.uk is a good place to start.
mistakes – building assistive experiences signi fi cantly safer than ones that take action directly. Copilot is designed to help you make better, faster decisions, not make decisions for you. No decisions
wrong? If an error occurs, is the user likely to spot it? What is the cost to the user if they don't? If detected, how easy is it to dismiss an error and move on? Can *you* measure a good or bad outcome? Design for failure
LLMs Hallucinations are unavoidable Mild hallucinations are very common Lots of techniques and tools exist for mitigating them Did I say they are unavoidable? They are *always* hallucinating, it’s just sometimes those hallucinations are useful. But can be reduced through a variety of techniques including tuning, prompting, context. Design for roughly 50% of the time. Severe ones less common, especially with grounding. Active area of research and development. Responsible development means only building systems where hallucinations aren’t dealbreakers. A quick aside about…
language models Many, many options to improve model outputs. Retrieval-Augmented Generation is probably the best ‘bang for your buck’. Most use cases *do not* require custom models. Grounded in reality
ff erent ways to do the ‘retrieval’ Essentially giving the model relevant input context Combined with links/citations can increase utility Allows base models to ‘work’ for specialised areas Typically much cheaper than other optimisations Keyword search, vector search, other ‘similarity-type’ searches. Steers the model outputs towards better/more relevant answers. Allow users to follow relevant links, decide which of them are most relevant. For example if the topic being discussed isn’t ‘knowable’ from public information. e.g., fi ne-tuned (or completely custom) models.
can power remarkable conversational experiences (e.g., natural language — source code). *But remember*, small hallucinations are very common. Only surprise if you can delight. Invite only
ELI5: Explain Like I’m Five. ELIKL: Explain Like I know Lots. ELIAPTDKMC: Explain Like I’m A Physicist That Doesn’t Know Much Chemistry. Explain like it’s me
arfon
bells17
andreiacsilva
medley
tanakahisateru
rkaga
mikemcquaid
pinboro
dora1998
kateinoigakukun
yucchiy
ypresto
spbaya0141
lara
swwweet
afnizarnur
jmmastey
destraynor
addyosmani
pedronauck
hatefulcrawdad
philnash
searls
myddelton
![Collaborations Workshop 2024 Thanks! [email protected] @[email protected]](https://files.speakerdeck.com/presentations/d2dabc2c6b3d474c909fd87d83c93572/slide_30.jpg){kind=link}