maxleedev (@maxleedev) / X

Pinned

maxleedev

@maxleedev

Sep 2, 2025

current chat interfaces suck, so i built a canvas for llms

00:00

This post is unavailable.

built an app to find how many degrees of connections you are from anyone on X

00:00

i wasted $200 on it 😭

00:00

This post is unavailable.

oh yay

By popular request: you can now branch conversations in ChatGPT, letting you more easily explore different directions without losing your original thread. Available now to logged-in users on web.

current chat interfaces still suck, so im building a canvas for llms added web search, cmd + f search, dark mode + more... join 5k+ others on waitlist: maxly.chat rolling out access next week

00:00

00:45

maxleedev

@maxleedev

Sep 2, 2025

current chat interfaces suck, so i built a canvas for llms

Replying to @maxleedev

so i built maxly.chat - a canvas for LLMs with parallel execution, branching memory, and real-time collaboration. the future of AI isn't a chatbox. it's a canvas

maxly.chat

LMCanvas: Compare AI Models Side-by-Side on a Visual Canvas

LMCanvas is a spatial canvas for multi-model AI chat. Compare ChatGPT, Claude, and Gemini side-by-side, branch conversations into parallel threads, and merge them back — all on an infinite canvas...

Replying to @ahadj0

like this

00:00

Replying to @maxleedev

p.s. i'm 18, previously engineered at 2 VC-backed startups, now looking for my next role. dm me if you're building something ambitious

Replying to @maxleedev

2. memory degradation - LLMs get worse as conversations grow. some queries need no memory, some need temporary context, some need everything. branching solves this

00:00

Replying to @maxleedev

current chat interfaces are fundamentally broken: 1. context switching hell - multiple questions = constant scrolling. by the time your first query finishes, you have 3 unread responses below. information gets lost in the chaos

00:00

Replying to @maxleedev

also on producthunt!

LMCanvas: A Canvas For LLMs | Product Hunt

who tf r these coders 💀

Kevin Xu

@kevinxu

Oct 11, 2025

fastest company to $100m arr or jail

Replying to @maxleedev

4. generative ui potential - design is limited as well. apply parallel queries to design and you can iterate through multiple ui variations instantly. not just one design, but multiple high-quality options to choose the best

00:00

Replying to @maxleedev

3. parallel queries - chatgpt forces you to wait for the current query to end before you can enter a new one. running queries in parallel saves massive time. why wait for one response when you can get multiple simultaneously?

32K