Hey all. TL;DR: none of this is super novel or fancy, but the set of a few simple approaches (cloud VM, tailscale for connecting, strong isolation, long-running sessions, basic notifications) made using agents with all tools enabled much more useful for me.
I hadn’t seen many practical writeups on running coding agents in cloud VMs specifically, so I figured it was worth sharing what actually worked day-to-day for me. I use this approach practically daily now
I tested ChatGPT Atlas as an alternative to writing a small scraper for collecting price distribution counts from Dubizzle (UAE Marketplace). It could extract correct numbers for a single filter, but consistently failed to repeat the same simple browsing steps across categories, hallucinating completion or stopping with vague time-constraint explanations. Curious if others have seen similar behavior with LLM-based browsing tools (or have had an alternative work for them)
This seems just like a single argument and counter argument against the sentience (or lack thereof) of AI today. I feel like the article lacks some broader views on the nature of sentience, and is quite narrow in its approach
Although, in fairness, I probably wouldn’t make a much better case for either of the sides
I observe that current AIs are not embedded in time, and while we may not be able to agree exactly what "sentience" and "experience" is, "change over time" seems a basic requirement: https://news.ycombinator.com/item?id=31727428
(Contrarians, or meta-contrarians, may jump up to claim otherwise, but I would say that while the question of what a non-temporal consciousness could hypothetically be may be fun to debate, it is also so far out of our experience that it is clearly not what we generally mean by the term and is therefore a completely different conversation.)
LLMs do not strike me as amenable to fixing this. But that only applies to LLMs, not to any future architectures.
I've been thinking about this and haven't found any fundamental difference.
Sure, LLMs don't have our fine temporal resolution, but GPT-4 (at least) knows the date, and can get the current time using Python when asked. And can tell the order of text events within a session. Our resolution has a limit too, somewhere under 1/25 of a second while awake, with much larger gaps when we sleep.
So it's a matter of degree, or more to the point it's how we might gerrymander definitions to suit us.
> One of the essential characteristics of general intelligence is “sentience,” the ability to have subjective experiences... Sentience is a crucial step on the road to general intelligence.
The problem, as usual, is that we don't have a solid understanding (or even definition) of what sentience actually is. The only thing that we can say with certainty is that we experience it.
This gives wide latitude for moving the goalposts by asserting a specific definition that is favorable to whatever it is you've built.
It gives an equally wide latitude for dismissing what's been built as not being actually sentient by defining "sentience" in a way that makes the dismissal true.
Hahahaha that's great. Yeah I see what you did there.
Originally I had mine in chat form but for various reasons, it seemed like an FAQ format with 'sources' resonated better. I could be wrong, but I think that makes OpenAI's custom GPTs an ill fit for the specific problem of networking.
Actually a company has been working on this for a few years now, and I believe they are currently in production. Their focus is football/soccer I believe. I was going to do a research internship at them before I dropped it for a different one. Here it is:
https://www.beyondsports.nl/
Looking at it, they heavily focus on tracking the movements of players now to replay in AR
I hadn’t seen many practical writeups on running coding agents in cloud VMs specifically, so I figured it was worth sharing what actually worked day-to-day for me. I use this approach practically daily now
reply