Realized I've reached the point now with GitHub Copilot autocomplete where I can often guess exactly what it's going to suggest, pause for a moment to wait for it to make the suggestion and accept it and move on It's majority a typing assistant now and I really like it for that
CODE
-
Tokenization Security Risks in AI Input Processing
By
–
I'm never 100% sure if that works or not – did that input get turned into those single tokens (arguably an injection security risk) or did it tokenize the input as "<" and then "gh" and so on?
-
New Book on AI Engineering with Foundation Models
By
–
I’m excited to share that I’m working on a new book about building applications with foundation models! AI Engineering builds upon Machine Learning Systems Design, but with a focus on large scale, ready made models. The book covers: – The new AI stack (e.g. how it differs from
-
Special tokens in AI: delimiters and use cases explained
By
–
Special tokens like these are used to delimit things like "this section is the user asking a question" vs "this section is an answer from the LLM" – or sometimes for things like "this is the output of a separate tool" I have no idea what those gh ones are for!
-
Understanding Tokenizers: The Vocabulary of AI Models
By
–
I wrote this explainer on tokenizers last year: https://
simonwillison.net/2023/Jun/8/gpt
-tokenizers/
… Effectively they're the vocabulary used by the model -
Multiday Coding Session Still Running Despite Crashes
By
–
it's still going fyi. can do multiday coding now but still crashes for unknown reasons. previous session ran for 6.6 days straight. still not done implementing like half of the pseudocode cc @walden_yan
-
Weights Biases Data Visualization Limitations Critique
By
–
weights & biases is great software but has anyone ever learned anything from one of these graphs? can't even see a correlation between two variables if their columns aren't next to each other
-
Host Any App on Spaces Beyond Gradio
By
–
you can host any app on Spaces (static web app, Dockerfile, etc) not just Gradio!
-
State Management for AI Agents: Side Effects and UX
By
–
state management is hard! we've been thinking a lot along the lines of staged side effects, io monads, and how to represent real world state changes as well. doing this right, with the right ux, will unlock a lot more user comfort with agents.
-
Hidden Reasoning in AI Interfaces Through Tag Parsing
By
–
If you control the interface, you can even have it reason within tags and then parse them out so the user doesn’t see.