> Without guidance, LLMs tend to paint themselves into a corner, because they’re generating code to solve individual prompts, not thinking holistically about an application’s architecture.
I've found I can prevent the LLM, in many cases, from thrashing on a bug/feature for long periods of time by switching into plan mode and, even in the middle of a conversation, having it reassess the structure around the problem, first. If you keep prompting about the same bug, it may keep producing variations of the problem code. But forcing it to stop and 'think' for a bit, has yielded much better results.
I've been finding a lot of ~5 year old satellite and street view data. It's only anecdotal, but it seems like Google is not updating their imagery as often as they used to.
I must believe, as with the medical profession's uptake of AI tools, if these tools prove themselves to be reliable and meaningfully helpful, she will experience more than enough professional influence to learn the tools.
Find people in her field who are already hopping on the wave. Better still, gently persuade her to find those people. She'll probably know where to look. In fact, I'd be surprised if her professional newsletters aren't already starting to surface those folks.
Measuring token usage as a productivity metric is like measuring keystrokes. Don't mind me, just over here rolling my face on the keyboard for an hour so I can take Friday off...
...except each keystroke has an associated cost, the sum of which may equal or exceed my salary.
What's nuts is how many intelligent people— people who would say "of course 'LOC written' is a terrible measure of developer productivity, of course only a dysfunctional company run by morons would do that"— have immediately bought into this. Amazon has token use mandates, I've heard Google has token use "leaderboards", friends at startups say they all get graded on tokens used. It's like watching your sensible, levelheaded friend go completely off the rails; collective madness.
I think that although we wish to consider ourselves as smart and really intelligent but we run on biological machines and clocks which evolutionary have not much of a difference since 1518 or even the times when we used to hunt and forage for that matter.
Some people respond to incentives. The rest of us are just trying to do our jobs and will probably be fired and then later consumed by the basilisk. We are living in an age of extremophiles.
+1 for NAND-to-Tetris. I combined it with a visual logic simulator so I could actually see the structures beyond the VHDL. I would love to go back and do Part 2.
I'm at 96% FSD miles since they started tracking a few months ago. It works very well. It was unreliable until about 12-18 months ago, but it's been great since v13.
GM/Ford/etc. driver assistance systems are nowhere close to the latest FSD. It would be nice if there were other options, but there isn't. You can't buy a Waymo. FSD can go from parked in the driveway to parked in a parking spot at your destination without any human intervention.
The steering wheel sensor could be defeated by taping a water bottle to the wheel. The eye tracking is supposed to be harder to defeat, although I wonder if it would accept a mannequin in the driver seat.
To be clear in the GitHub thread Don Ho repeatedly encouraged him to do this, and said it was cool that he was trying to bring Notepad++ to Mac! Just don't make it look like Don Ho and the rest of the team is responsible for any quality issues. Don't use the logo!
My dude, go grocery shopping with a 2-year-old and see if you want them walking around. They'll be peeling a sticker off the floor for two minutes, then grabbing everything off the shelf. It's perfectly normal to cart the kid around so you can actually make progress through the aisles. They can reasonably follow you around between 3-4.
OP said “how can a child that can't even walk yet have the practice to know how to skip the ads.” A two year old should definitely know how to walk. Obviously you will not have it strutting around in a store, but it should know how to walk.
Also I don’t let my two year old near screens on her own, and generally do not allow screen time at all, but she absorbs things at a pace which is incredible. If I were to “skip ads” in front of her, I’d only have to do it around twice for her to be able to do it on her own…
Also, my 2 year olds walked around the store all the time, as well as sat in the cart when I didn't have time to supervise. It is good exercise, and helps them practice following instructions.
They just leave them outside in the stroller in someplace like Sweden. It's hilarious how on HN the nordic countries are idolized and leaving strollers outside while the kid stares at the street man smoking fentanyl out of a piece of aluminum foil indicates you are a glorious liberated member of intelligentsia but by god if you put a tablet on to get a moment of peace while you take a shower then you are a hideous sub-human piece of garbage.
Babies. They leave there babies. They do not leave there two years old already fully capable to toddle away and still dumb enough to walk into anything.
Also, not every city has the same massive drug addiction homelessness problem as yours.
In most countries it's illegal to leave any child unattended in a way that puts them at risk which is a vague definition. But if something were to happen to the child while unsupervised any vagueness collapses into negligence. A baby will sleep in the pram, but for a toddler to be abandoned alone strapped in the pram is capital punishment.
I've found I can prevent the LLM, in many cases, from thrashing on a bug/feature for long periods of time by switching into plan mode and, even in the middle of a conversation, having it reassess the structure around the problem, first. If you keep prompting about the same bug, it may keep producing variations of the problem code. But forcing it to stop and 'think' for a bit, has yielded much better results.
reply