LLMs Decode Garbled Text From Shifted Keys Or Wrong Keyboard Layouts
Reactions from ranked influencers
2 posts
models are truly superhuman at reading garbled text you can type on your keyboard but all your fingers are one key too high, works fine even typing in English while your keyboard is set to Arabic, which looks like complete gibberish, is no problem
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.
credit to @mehran__jalali for first finding the arabic typing in english trick, which i think first worked with o3