One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
@XFreeze Multi model fusion plugin for grok build polished up and limited verification harness & test artifact linked
https://t.co/1t7n3xU6fI
Works with openrouter, trusted router & direct provider API key
Would love to hear what u think
@ShadowofEzra Delusional fake prophecy lead by fake Jew, non Israelite Bolshevik psychopaths hell bent on satanist Baal, Talmudic, gay retardation with blatant subversion of monetary, religious & ideological systems. It will be continuously ridiculed & eventually declared war upon.