Hallucinations/inaccuracies

 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 determining 

the duration of the required stimulus to be felt. Also, the results of the

study suggest that the stimulus needs to be presented with a sufficient 

temporal duration to be felt.


john@john-GF63-Thin-11SC:~/ai$ ./scripts/ollama_summarise_one.sh SAMPLES/hawaiiarticle.txt 

Sure, here is the paragraph you requested:


> The duration of a threshold stimulus of course depends on stimulus 

intensity. I used the 250 (or 300) msec number because it is my 

recollection that in almost all of his backwards referral experiment that 

is the duration he used. So in an effort to get to the essence of the 

issue that's the number I quoted. Glynn made that point a long time ago 

and it was the main point of my plots in the Tucson III Proceedings. And 

it was the main point of the analysis that McCrone made of his data.


john@john-GF63-Thin-11SC:~/ai$ ./scripts/ollama_summarise_one.sh SAMPLES/hawaiiarticle.txt 

Sure, here is a summary of the passage:


The passage discusses the temporal delays involved in sensory perception 

and backward referral experiments. According to Libet et al. (1964), the 

duration of a threshold stimulus of course depends on stimulus intensity. 

With a stronger stimulus, the required duration is much shorter than 250 

ms. However, when the stimulus intensity is lower, the required duration 

is longer. The passage also discusses the implications of Libet's data, 

such as the sloppiness of the details and the importance of considering 

the stimulus intensity when conducting these experiments.

Popular posts from this blog

Recent Experiments testing ChatGPT's limits and some useful prompts

Introduction ChatGPT has a lot of people excited, but it deserves this level of excitement. It has a number of faults which I list below - some with workarounds - but in general it is amazingly good. It is absolutely not for having fun chatting to a robot, it's really more like a brilliant coworker who is incredibly stupid at some quite mundane tasks, but incredibly good at more tricky tasks. Summary of findings so far.  1. API vs Interactive Version - a caution 2. Coding Strengths and Weaknesses - be very careful but very useful anyway 3. Shell Scripting - amazingly good, probably what it's best at 4. Text Summarisation - fiddly but useful 5. Spreadsheet Analysis - annoying, maybe do by hand 6. Multi-Step Instruction Handling - very annoying 7. Spellchecking and writing style/grammar - ok overall but fiddly 8. File Compatibility and Formatting - not great 9. APA References from DOIs - good 10. Reference Accuracy - bad, double-check its work 11. Tone and Style Adaptations - ex...
Read more

Testing ChatGPT on coding - a script to make CSV to ICS

 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...
Read more

Ollama3 works - running a local LLM

Do this: curl -fsSL https://ollama.com/install.sh | sh ollama create llama3  It will then download the llama3 model, about 4.7 gb to run it: ollama run llama3  if you want it to read and summarise a textfile called textfile.txt: ollama run llama3 "Read the text file $(cat textfile.txt) and summarise the findings in one paragraph of no more than 300 words"  And here's a gui for it: https://github.com/amithkoujalgi/ollama-pdf-bot The system runs as a service (daemon) on Linux. CPU usage is high but not bad and response time much better than localGPT. It stores the model files (large LLM blobs) in  /usr/share/ollama/.ollama/models The models can be dowloaded from huggingface.io or https://ollama.com/library
Read more