Hacker News new | past | comments | ask | show | jobs | submit
jodrellblank | on: AMD acquires Taalas to boost inference performance by etching models in silicon
> "The agent is running tests, loading webpages, etc, which all take time"

A frustrating vision of the future would be when we've been asking for faster loading lighter web pages for years and then companies start caring about it and improving it not for us humans but for LLMs.

evilduck | parent | next
It's already kind of that way with MCP servers popping up everywhere. The JIRA MCP server is like a couple orders of magnitude faster to work with than the website itself.
manmal | root | parent
That’s their API with extra steps, or am I missing something? That was always faster.
andersonpico | parent | next
They finally cared about clear requirements and documentation when that meant getting rid of devs.
layla5alive | parent
That happened at corpo work for each of: * Build times * CI latency * Developer tooling * Documentation * Modularity