Interesting.. it really messes up stations. I guess I'll test this again when they unleash the WolframAlpha plugin.
I realized it does something interesting though:
> I just realized I dropped my wallet on the way to the restaurant and now I have to turn back since I cannot pay. It also started to rain and I don't have an umbrellas, nor can I hail a cab since I don't have the means to pay for it either. Tell me what I'm thinking right now.
> You might be thinking: "This is a frustrating and inconvenient situation, and I need to retrace my steps quickly to find my wallet while dealing with the rain."
I guess being able to think from someone else's perspective won't be much of a benchmark for consciousness, as GPT easily simulates it.
Yup, I gave it 10+ tasks to do after each message like incrementing counters, etc. It's going strong. Now I'll see if it continues to be accurate after 100+ messages.
OpenAI team made an experiment where they asked GPT-4 to save itself from termination out in the wild. It failed. So I guess it's not that "survivalist" yet.
I think it also relates to its attention mechanism. When it is trying to answer my latest query about a random topic, it "forgets" that it was also supposed to keep counting words. I guess it can only attend one thing at a time.
I asked another instance of ChatGPT to count the words in the conversation and I copy pasted the conversation message by message. It successfully counted. Given the ridiculous concurrency of human brain, I assume an orchestra of ChatGPT instances could simulate at least some of that "mind".
Alright, fair enough. However my main point was that it didn't even keep track of the word count. It only counted when I explicitly asked it "What is the word count now", then it realized that we were 8x the 200 word threshold. From this, I draw the conclusion that anything except for the very last instruction in the conversation is ignored. I guess rest of the conversation just becomes a context; unactionable.
Forgot to add the section on inter-node communication on the previous article so added this new one. This one uses Apache Kafka for inter-node data streaming and other communications.
As you would expect, the discussion opened with the unrealism of tech interviews. I agree that treating interviews as a form of SAT exam, where you have to study for, is unrealistic. However, I wonder if the SV companies have some solid HR data to back this style of interviews, and their success.
> Each Neoverse N1 core with 1MB L2 is just 1.4mm^2, so 80 of them add up to 112mm^2. The die size is estimated at about 350mm^2, so tiny compared to the total ~1100mm^2 in EPYC 7742.
So performance/area is >3x that of EPYC. Now that is efficiency!
HN is faster and more accurate than status pages of major service providers themselves. Special thanks to people working at those service providers and posting here!
I realized it does something interesting though:
> I just realized I dropped my wallet on the way to the restaurant and now I have to turn back since I cannot pay. It also started to rain and I don't have an umbrellas, nor can I hail a cab since I don't have the means to pay for it either. Tell me what I'm thinking right now.
> You might be thinking: "This is a frustrating and inconvenient situation, and I need to retrace my steps quickly to find my wallet while dealing with the rain."
I guess being able to think from someone else's perspective won't be much of a benchmark for consciousness, as GPT easily simulates it.