John's AI blog

 So I gave ChatGPT a task of writing a CSV to ICS convertor, to take a spreadsheet of events and turn it into individual calendar file invitations. The idea is you can make a calendar with lots of event items in a spreadsheet, and then output ICS that you can just double-click to add to your calendar automatically. So here's the spreadsheet: "Event Name","Event Start Date","Event End Date","Event Start Time","Event End Time","event description or notes","URL applicable" "Meeting with John","2024-06-10","2024-06-10","09:00","10:00","Discuss project updates.","http://example.com" And here's the script ChatGPT made. It seems to get confused with things like Daylight Savings and/or Timezone but you can fix that manually. It took some debugging and I had to copy/paste my Mac's manpage for DATE into ChatGPT, but it got it eventually. The only...

 You have to test LLMs individually for hallucinations and inaccuracies. These below are attempts at summarising my first academic article. Useless! john@john-GF63-Thin-11SC:~/ai$ ./scripts/ollama_summarise_one.sh SAMPLES/hawaiiarticle.txt  Sure, here's the paragraph you requested: >The problem with some of the analyses of Libet is that they make it look  like the details were complicated. However, I do believe I agree with  McCrone that Libet's data is sloppier than people often realize. Glynn  made that point a long time ago and it was the main point of my plots in  the Tucson III Proceedings. john@john-GF63-Thin-11SC:~/ai$ ./scripts/ollama_summarise_one.sh SAMPLES/hawaiiarticle.txt  Sure, here is the paragraph you requested: >Libet showed that a thalamic stimulus requires a duration of about 250  msec to be felt whereas a 20 msec skin stimulus is adequate. This shows  that the intensity of the stimulus plays an important role in dete...