Yeah so turns out there's still no way to hold an infinite amount of information in your head for free

The structure of code can be so beautiful

The DSP framework also had some extensive work on using LLMs to generate their own examples: arxiv.org/abs/2212.14024

ngl Continuum on a gigantic codebase is such a fire experience

It's so confusing to me how powerful and yet underdeveloped GPT function calling is. Like this thing was fine tuned to use tools at a cost of probably hundreds of millions, but it can't guarantee valid JSON output and there's no first party methods for counting token usage

Check out our fucking badass new landing page. The mesh returns at continuum.sh

Every other day a new paper comes out that claims to solve context window limits or RAG with some fancy sounding technique, and then when you actually read the paper it's just 2000 lines of Python doing recursive summarization in a slightly different way

So many problems are provably undecidable and yet you gotta just find partial solutions anyway

🚢 New Continuum version🚢 ✔ Sleek new UI (shoutout Daniel Kuntz) ✔ Code knowledge graphs for Python projects ✔ GPT-4 Turbo with 128k context window Excited to see what you all build with it!

Many are saying this

Reverse engineering mode coming soon 👁️‍🗨️

json (dadtime) you should try Continuum it's incredibly goated

React side-effect chains so fucked you need a captured machine god to understand them

Continuum is the only AI developer assistant that supports live architectural & sequence diagram generation. Try it just by asking for a diagram of any part of your system!

Continuum now supports binary decompilation! Upload any binary to ask questions about it. Beta is live for all users — only decompile things you have permission for 😉

gm anon Continuum has been updated with Solidity support! Try it out now to understand your favorite Ethereum smart contracts and quickly develop new ones.

Intern submitted another 70,000 line change with no comments? No problem! Continuum now supports interactive pull request analysis