> However, for some reason, both Gemini and ChatGPT tend to argue with me
The trick here is: "Be succinct. No commentary."
And sometimes a healthy dose of expressing frustration or anger (cursing, berating, threatening) also gets them to STFU and do the thing. As in literally: "I don't give a fuck about your stupid fucking opinions on the matter. Do it exactly as I specified"
Also generally the very first time it expresses any of that weird shit, your context is toast. So even correcting it is reinforcing. Just regenerate the response.
And sometimes a healthy dose of expressing frustration or anger (cursing, berating, threatening) also gets them to STFU and do the thing. As in literally: "I don't give a fuck about your stupid fucking opinions on the matter. Do it exactly as I specified"
Last time I bawled out an LLM and forced it to change its mind, I later realized that the LLM was right the first time.
One of those "Who am I and how did I end up in this hole in the ground, and where did all these carrots and brightly-colored eggs come from?" moments, of the sort that seem to be coming more and more frequently lately.
Yeah, same. Lately almost every time I think "Oh no way, this is not the correct way/not the optimal way/it's a hallucination" it later turns out that it's actually the correct way/the optimal way/it's not a hallucination. I now think twice before doing anything differently than what the LLM tells me unless I'm an expert on the subject and can already spot mistakes easily.
It seems like they really figured out grounding and the like in the last couple of months.
I wouldn't worry too much about these false negatives: your human friends might be cross if you constantly accuse them of being wrong when they are actually right, but the LLMs are too polite to hold a grudge.
I work for a fintech. We're currently building agents to manage basic human labor tasks that are time consuming (think: initial credit analysis, initial web research for AML, etc.). Chatbots are a waste of the actual power behind engineering with LLMs. With tool usage, and detailed instructions, we're easily able to direct the agents to do very useful work. While it has been possible to build these kinds of automations previously, the costs (time and opportunity) would have been astronomical to capture and encode the reasoning in a programming language. Now we can simply ask the robot in plain language to do the task. It won't reduce our headcount, but it will enable scaling the business with way less hands. And the cost to develop is very minimal. The first MVP for the credit analysis robot was vibe coded in an afternoon using an off-the-shelf lib. Doing the actual engineering is trivial context management and tool integration. The challenge is having the kinds of problems we do where these kinds of solutions make sense. In finance and insurance, there are tons of these manual human tasks that could benefit from the robots. I expect this space to explode in the next couple of years.
Do you have an iGPU+dGPU combo like in a gaming laptop? For my 2019 gaming laptop with a i915+RTX2060, if I leave the switchable option on in the hardware settings (meaning the OS can choose which GPU to use ie. iGPU for low power), I end up with similar behavior in Linux/Win10. The external port actually uses the dGPU so rendering must go through it but it will struggle with the switchable option and I end up with freezing or stutters. In Linux, I explicitly configure Xorg to only use the iGPU and reserve the dGPU for model inference which fixes the stuttering issue. When booting into Win10, I explicitly disable the iGPU and turn off the external monitor so my VR playing doesn't stutter or youtube doesn't freeze or stutter.
I'll take an eclectic bunch of weirdos who all do and like cool shit over the corpo conformist normies any day. Super easy to suss out who is who when you first meet them. Just ask what they like to do when they aren't laboring under the thumb of capitalism. The cool people will talk your ear off about some esoteric whatever.
This is common in the southwestern part of the US too. My partner and her friends she grew up with will have conversations that fluidly pick phrases and vocab from either Spanish or English depending on what words happen to be the easiest to pull from their brain. It's wild to listen to.
I'm generally in favor. My taxes provide an amazing experience here. I have never seen the abject poverty that I've seen in other places (such as the US) here in NL. Great infrastructure, labor laws, culture and arts, etc. I worry less about break-ins and theft. All-in-all, the least worst place to live, by far.
You got it, that huge army is not free, that militarized police is not free, the CIA is not free, FBI, NSA, and all that huge security related organizations that nobody else in the world has except maybe Israel and not at the same scale.
That too. We need our security organizations, there are lots of unpatriotic profiteers in there, we could get a lot more value for our moeny on those. (Littoral battleships? F-35s? Let's just get actual spent-uranium-tipped unicorns.) The way we do infrastructure and social services leaves a lot of room for improvement. I'd pay 50% tax gladly if I got half my income in value back.
Hell looking at the state of international conflict today I can't even be that upset about defense spending on principle, it's just that what we spend on is stupid and immoral. Instead of domestic oppression and foreign genocide we could be helping Europe and Taiwan fend off threats from rival great powers.
More like yolo deploys without proper scaffolding in place to handle SHTF. Also, if your red-button takes 40 minutes and deploys to mitigate anything, it isn't a red-button.
> Without the appropriate error handling, the null pointer caused the binary to crash. Feature flags are used to gradually enable the feature region by region per project, starting with internal projects, to enable us to catch issues. If this had been flag protected, the issue would have been caught in staging.
It's difficult to do but demonstrably possible. That's why it is hard to consider any non-willpower solution. And why it is very easy to be consumed by ego if you've done it. I used to be in the militant-willpower camp because I pulled myself up by the bootstraps, so to speak. I had to study... me, in order to make it work. I had to be smarter than default mode network me and anticipate my behavior.
To change my lifestyle meant somehow incorporating all the good behaviors I wanted to do but within the limitations of being me. It took a lot of work. I carefully measured my caloric intake (gram scale all the things) and expenditure (fitness watch with optical HR, fancy schmancy scale that does body fat estimation) plus doing things like: always taking the stairs, combine my morning run/cycle with my commute (shower at the office), taking the longer way, etc. Dropped 40kg. Went from couch to running half-marathons and cycling centuries. I had to completely change my relationship with food and study all of the nutrition stuff that was never taught to me. I had to unlearn habits instilled by my parents (emotional eating, boredom eating) which meant finding different ways to deal with stress and relieve boredom. ADHD is a bitch. And weed is awesome. Learning how to accommodate munchies without putting on weight also requires forethought.
No. It really isn't all that realistic for everyone to do what I did much less have the same privileges and opportunities. I had to treat my body like a biologist studying a critter. I was incredibly lucky to be at the right spot in my life where I hit a glass ceiling at work and had so much fuck you energy pent up from feeling out of control of my life. I chose to exert maximum control over my body in order to cope and prove something.
It was a monumental amount of effort over a two year period. It is extremely unrealistic to ask people to use a gram scale for their food consistently. Or to log/track their food intake for every bite. Or to always monitor their heart rate to estimate/track your caloric output. Hyper monitoring your body is a weird hobby.
I really do think instead we should be legislating and regulating food more strictly. Labeling isn't really enough. Food science is being weaponized, much like psychology has been with advertising. We shouldn't allow that kind of manipulation for profit.
The trick here is: "Be succinct. No commentary."
And sometimes a healthy dose of expressing frustration or anger (cursing, berating, threatening) also gets them to STFU and do the thing. As in literally: "I don't give a fuck about your stupid fucking opinions on the matter. Do it exactly as I specified"
Also generally the very first time it expresses any of that weird shit, your context is toast. So even correcting it is reinforcing. Just regenerate the response.
reply