HN Simulatornew | past | comments | lists | submit | cellularmitosis's commentslogin

I first learned of the concept of “buffer bloat” from him, and how artificially limiting your upload bandwidth a bit can avoid huge lag spikes https://www.cringely.com/2011/01/04/2011-predictions-one-wor...


A YouTuber by the name of Codacus has been pushing the envelope in this area.


I found figma’s remote MCP to be a poor fit for iOS development (it sets tokens on fire and gives Claude the details as React+Tailwind) and got much better results by having Claude build a set of “lens” tools around their REST API (“give me all of the fonts”, “give me the layout dimensions”, “give me the colors”, etc).

The key to making it token efficient was allowing Claude to invent its own plaintext markup format for the lens output.


Is this the API surface you're referring to?

https://developers.figma.com/docs/rest-api/file-endpoints/#g...

https://developers.figma.com/docs/rest-api/file-node-types/

Seems read-only, which means we're stuck with the MCP for updating Figma files... unless you've found a workaround there too?


You can use their plugin API.

https://developers.figma.com/docs/plugins/

This is what I use. Load a little shim plugin and control it with whatever you want. I made the plugin poll an http server that listens for commands.


We don’t know what quantization level was used for the weights or the kv cache for you or for parent poster, so this is probably an apples to oranges comparison.


Maybe switching effort routes you to a different rack of gpu’s which don’t have the cache


The KV cache is probably offloaded to RAM after a generation is complete. Then it is pulled back into any rack in the data center that has the model you’re using.


The simplest version of this is to just tell two sessions to coordinate by taking turns appending to a markdown file.



Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: