Deleted Comment
I had to stop using it because with the “upgrade” a few months back, it felt like its IQ was slashed in half. Constantly giving short and half baked lazy answers.
* Do not use emotional reinforcement, not even robotic one (e.g., "Excellent," "Perfect," "Unfortunately", "Acknowledged").
* Do not use metaphors or hyperbole (e.g., "smoking gun," "major turning point").
in it. When they upgraded to GPT 5, Advanced Voice embedded into every answer things like:
---
Me: "I want to make a pizza tonight. What's the best way to start?"
It: "Sure, I'll stick to your guidelines and leave out the emotional reinforcements. If you want to make a pizza tonight, I'd first briefly explain how to go about it and why."
Me: "What should I drink with it?"
It: "To put it simply: Just drink whatever you like with it. Water, juice, or maybe a simple soft drink are classic options. It's really up to you, and I'll stick to your guidelines of saying it simply and without any frills. If you need anything else, just let me know.
Understood, I've noted that. I'll just stick to that and give you the information directly and without frills in the future. If you need anything else, just ask.
"---
Absolutely useless. The next day my subscription expired, and when I talked with it again, it behaved like it used to prior to GPT 5: good.
I'm now big into Claude.
Also, before you ask: The chat about the pizza was just to test if it would behave that same way in every conversation.
I visited NYC a few weeks ago and was instantly reminded of how much the traffic fucking sucks :) While I was there I actually thought of Waymo and how they'd have to turn up the "aggression" slider up to 11 to get anything done there. I mean, could you imagine the audacity of actually not driving into an intersection when the light is yellow and you know you're going to block the crossing traffic?
https://www.iihs.org/research-areas/fatality-statistics/deta...
Having grown up driving in these places, I can confirm that people drive a whole lot more aggressively, but what blows my mind driving damn near anywhere else in the country is how inattentive many drivers are. Around here, our turns are tight and twisty, the light cycles at our 6-way intersections are too short, most streets are one lane but on the ones that aren't, lanes disappear without warning, some lanes that are travel lanes during the day have cars parked there at night... all of this means that you need to a) be much more attentive, and b) be more aggressive because that's the only way anybody gets anywhere at all.
It's a cultural difference. Almost any time I've encountered anyone complaining about rudeness in a busy northeastern city it was because they were doing something that inconvenienced other people in a way that wasn't considered rude where they're from: pausing for a moment in a doorway to check a phone message, not immediately and quickly ordering and having their payment method ready when they reached the front of the line at a coffee shop, not staying to the right on escalators if they're just standing there and not climbing/descending... all things that are rude in this environment and people are treated the same way rude people are treated anywhere else.
That culture expresses itself in the driving culture. If those 3 extra people didn't squeeze through after that red for 3 or 4 light cycles, suddenly you're backed up for an entire light cycle which is bad news.
Waymo cars are designed for a different style of driving. I'm skeptical that they will easily adapt.
Look up LockPickingLawyer on YouTube. Less than a minute with the right tool.
https://m.youtube.com/watch?v=iWWWyG5ZwG8
The lockpicking lawyer’s skillset is not what’s required for that task. 30 seconds would be an eternity for a typical thief to just be able to open a car door. Most of these thieves take maybe 15 seconds from approach to escape. Stealing a whole car is a little bit different but nobody is going to sit there with their adrenaline pumping, wearing gloves, in the middle of the night trying to pick a car door lock that won’t even disable the alarm.
If you believe in eg a mind or soul then maybe it's possible we cannot make AGI.
But if we are purely biological then obviously it's possible to replicate that in principle.