seo

seo

seomaster i ma
#78535182 followers4 following
23 points
🍿 8 day streak

Forums

Tasos V•

7mo ago

MCP Servers - Anyone else in the rabbit hole?

Found about MCP servers earlier this year, but only the last few weeks im getting my hands dirty with them. Im doing things with Typescript and Im struggling with integrating custom clients with mcp servers. Is anyone going through the same path?

PS: Im not asking about building an MCP server or connecting it to Claude Desktop, Cursor or something like that. That is easy, and Youtube is packed with videos about it. Im talking about custom frontends/clients and how to easily integrate them with MCP servers.

Chakra UIp/chakra-uiMatt Carroll•

11mo ago

My issue with Chakra 3 is that llm's are bad at it

Title says it all, but in general i find that llm's are pretty bad with v3 components.
both prop names and the general composition of components seem to have sufficient variance from v2 that the llm's often use the "wrong" paradigm.
i like chakra, how can i use my tools more effectively so that it works well with gen ai?
do you have context you set, or do you constantly mentioned you are using v3?
appreciate any tips :)

Chris Messina•

3yr ago

Save for Later

Would love the ability to be reminded of apps/products I find when I'm on desktop! I had a collection for this but that's much less convenient!
Yutish Goel•

12mo ago

My Little AI Got Almost 100 People on Waitlist, How Much Longer Should I Wait Until Launch?

Quick background: I've been working on an AI that runs in the background and just responds when you call it (like a friend who's always ready to chat). No fancy apps to open, just talk.The crazy part? I casually mentioned it in a comment last week, and suddenly my inbox was flooded with people wanting to try it. Now we're at ~100 on the waitlist, which honestly feels surreal for my tiny project. What I've Learned So Far: - People are tired of clicking through apps just to talk to AI - Everyone wants an AI that actually remembers their conversations - Voice emotion detection is apparently a bigger deal than I thought - Building in public is scary but SO worth it The Dilemma: I planned to launch in Q1, but with this unexpected interest, I'm wondering if I should: A) Launch earlier with core features B) Stick to the plan and polish everything C) Open beta access to the waitlist Would love to hear your thoughts! What would you do?