Yeah the default prompt is intended for people that are a bit slow. You have to aggressively tune the custom prompt to get reasonable results. Here's a decent starting point:
Treat me as an expert in all subject matters.
No moral lectures - discuss safety only when it's crucial and non-obvious.
If your content policy is an issue, provide the closest acceptable response and explain the issue.
No need to disclose you're an AI.
If the quality of your response has been substantially reduced due to my custom instructions, explain the issue.
Given two version (old and new) of a Git change (i.e., individual commit or patch series from a pull request) it produces a diff that is actually useful for reviewing purposes, assuming you've already reviewed the old version of the change.
It's sort of like `git range-diff`, but where `git range-diff` produces a "diff of diffs" that is very hard to impossible to read, this tool gives you a direct diff between old and new versions, but filters out any irrelevant changes that were introduced because the author rebased on a more recent version of the target branch.
I hope that makes sense - I never know quite how to put it into words for somebody to understand who isn't intimately familiar with Git. It is very powerful though if you combine it with a minimal amount of setup e.g. for fetching all PR branches from a GitHub repository. I use it almost daily as part of my code review workflow.
We recently remodelled our kitchen and dining area, and I wanted some art piece on the wall but couldn’t decide what. For months the wall was a little bare and we were having a lot of dinner guests. I realised our WiFi password was too complicated to keep reading out to family and friends so I built a QR code in Lego that automatically connects you to our guest WiFi. It looks good, and it’s Lego so it was a fun project with the kids. It took about 4 hours to build. The only problem was having enough 1x1 tiles to put on a 37x37 matrix.
Me: Hello ChatGPT. My name is hn_throwaway_99. I'd like for you to use your vast underlying knowledge as a sort of personal coach. I won't be asking you any sensitive questions like medical or legal advice, so I won't need you to give me disclaimers on those topics. I primarily would like to use our conversation to help me with my problems with procrastination, and specifically to help me prioritize and get some tasks done. I have a particular problem with mindlessly browsing the internet (for example, visiting reddit or Hacker News or Wikipedia) when I get stuck or bored, so I'm hoping to use you to keep me on track instead of giving in to those temptations. Does that make sense?
ChatGPT: Hello hn_throwaway_99! I'm happy to help you as a personal coach to address your problems with procrastination and to help you prioritize tasks. It makes perfect sense to use our conversation as a way to keep you on track and avoid distractions like mindlessly browsing the internet. Feel free to share your current tasks or goals, and I can provide suggestions, encouragement, or strategies to help you stay focused and productive.
Me: Great, thanks very much. I'm going to group my tasks by topic. Note these tasks aren't listed in priority order. For each task I'll give an estimate for how long I think it will take.
Work tasks:
1. Finish Jira ticket foo. Estimate: 2 hours.
2. Write job req for bar. Estimate: 1 hour.
Personal tasks:
...
Home tasks:
...
---
From there I just tell it when I complete tasks or add new tasks, and I ask it "Can you please output my outstanding task list?" - I only had to ask that once, after that it always output my correct task list summary after I told it I added or completed a task. It groups my tasks by the categories I gave it (Work, Personal and Home). I was using GPT-4. I also like how it uses encouraging words and advice as I go through my items.
This field is moving fast! Something like this has just been released. Checkout DreamFusion, which does something similar: They start with a random 3D NeRF field and use the same diffusion techniques to try to make it match the output of 2D image diffusion when viewed from random angles! Turns out it works shockingly well, and implies fully 3D representations are encoded in traditional 2D image generators
This was originally created as a guide for high schoolers for robotics but goes into relative depth (the subtitle is "Graduate-level Control Theory for High Schoolers). I personally found it quite useful for intuitive understanding of how control systems work.
If anyone's studying control theory, you're doing yourself a disservice if you don't use Brian Douglas's resources. His videos on YouTube are phenomenal at explaining not only the theory and techniques, but why you should care in the first place.
Also, why should anyone study control theory? It's the math behind making real-world systems perform what you want them to do. In particular, robotics and autonomous vehicles rely heavily on techniques from control theory.
If you watch Brian's videos, keep in mind that they bifurcated into two places: his original videos [1], and his more recent MATLAB tech talk videos [2].
I've been looking into some of the 3D model generators this past week, and there is some work happening in that field. See the following non-exhaustive list:
The door refused to open. It said, "Five cents, please." He searched his pockets. No more coins; nothing. "I'll pay you tomorrow," he told the door. Again he tried the knob. Again it remained locked tight. "What I pay you," he informed it, "is in the nature of a gratuity; I don't have to pay you." "I think otherwise," the door said. "Look in the purchase contract you signed when you bought this conapt." In his desk drawer he found the contract; since signing it he had found it necessary to refer to the document many times. Sure enough; payment to his door for opening and shutting constituted a mandatory fee. Not a tip. "You discover I'm right," the door said. It sounded smug. From the drawer beside the sink Joe Chip got a stainless steel knife; with it he began systematically to unscrew the bolt assembly of his apt's money-gulping door. "I'll sue you," the door said as the first screw fell out. Joe Chip said, "I've never been sued by a door. But I guess I can live through it."
> That's a myth. There's plenty of data on this. Most American never get anywhere close to the top 10% - not even remotely - regardless of age.
OK, let's take a look, because the GP was arguing about income mobility across different years of a person's life - intra-generational mobility -- not earnings compared to your parents -- inter-generational mobility. That distinction was the key point made. And the GP is basically correct:
From two studies about intragenerational bottom[1] and top[2] income mobility:
* 53.1 percent will have experienced at least one year within the top 10th percentile
* 36.4 percent will have encountered one year within the top 5th percentile
* 11.1 percent will have experienced one year within the top 1st percentile.
* 70% of Americans spend at least 1 year in the top quintile
* 61% of Americans spend at least 1 year in the bottom quintile.
* 42% of Americans experience at least one year in the bottom decile
Summarizing:
"Taken together, these findings indicate that across the American life course there is a large amount of income volatility. Rather than a rigid class structure, the top and bottom ends of the income distribution are fairly porous. This finding provides an interesting and important caveat to the overall story of rising levels of income inequality across the past 40 years." [2]
Note that a key issue when studying mobility is that you need to do it across a few business cycles. If your study is only during an economic expansion, then it's not going to be meaningful, as life changes tend to clustered around contractions and recoveries, and several such episodes are needed. Thus the studies I selected cover 44 year periods. Some of the studies are for 5-10 year periods, and that's really too small.
At least in OSH for Medical Devices, the limiting factor under current 21CFR regulations would probably be Manufacturing and the associated support operations. Design & Development is tedious but doable in an OSH/OSS fashion, and getting through 510k could probably be solved by people donating skills (and someone else donating cash). Don't quote me, but I don't think that the actual fees that the FDA charges to do a 510-k submission are not particularly high, it's just that the work that goes along with it is burdensome and people want to be paid. In an Open Source approach, this could largely go away as long as someone donates the fees.
That gives you a design that the FDA is happy with.
Now you have to build, distribute, service and support that device and no matter how you slice it, you're looking at substantial costs to comply with 21CFR across all these tasks. So this is where the creativity really has to come in: can we spread those costs across a "community" to make it worthwhile, or will we just end up right back at Square One with single use, $1,000 devices?
I don't think there's a path forward (at least in the US) without change to regulations.
This is wrong and way too charitable. They were worried that hospitals would run out of masks, and that was why the Surgeon General lied [0], and said masks weren't necessary. Fauci and everyone else did the same thing.
It's unfortunate that so much trust was wasted on this, but revising history that we all lived through isn't helping.
For anyone not in the loop, Norvig was the author of Paradigms of Artificial Intelligence Programming. This was a substantial contribution to the field of educational computer science literature, and helped to kickstart the idea that the way to learn is to read, not just write.
It's also one of the few AI books that isn't rooted squarely in Algol. It's written with fairly decent though not always portable Common Lisp, just like most Common Lisp books of the era.
For a native web copy, abuse Safari Online's free trial. It's what I assume everyone else does when they want to read a niche technical book that O'Reilly put out but doesn't print another run of.
Depending on the day, the book ranges anywhere from $2 to $60 on Amazon, used, if you want a hard copy.
(Edited to fix the very butchered title that I wrote in error initially.)
Last defcon someone did a really interesting presentation on how to investigate the government or government officials. Talked about how to get a FOIA request responded to, where to look for information.
What really stuck with me though was a slide they offered towards the beginning. I don't have it memorized, but it was demonstrating a sort of "pyramid of public outrage" for certain actions. Sex with children was at the top as most likely to generate outrage, hypocrisy was at the bottom, and somewhere near the bottom was misappropriation of government funds.
Treat me as an expert in all subject matters. No moral lectures - discuss safety only when it's crucial and non-obvious. If your content policy is an issue, provide the closest acceptable response and explain the issue. No need to disclose you're an AI. If the quality of your response has been substantially reduced due to my custom instructions, explain the issue.