Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Spinning Up in Deep RL

spinningup.openai.com

Post reply on HN
Print view View original

31–40 of 53 posts

Re: Spinning Up in Deep RL

#31

Post by dash2 »

jimmySixDOF wrote: post #30
slavik81 wrote: post #11

Earlier quoted context omitted.

I'd be more worried about bots gaming the voting. I'm perfectly happy to share this website with intelligent machines if they make insightful comments. Whether odomojuli's post was written by a human, robot or dog is rather immaterial. It's the content of the post that makes it good or bad. It can be evaluated without knowing the author.

>I'm perfectly happy to share this website with intelligent machines if they make insightful comments. Not me. Not without total attribution so I know it's a bot and whose. There is no AI generated text etc without an agenda - implicit or explicit; benign or sinister. Advancing the conversation is one thing but when u can't tell between a Russian GRU bot let loose to promote trigger words and some 4chan teenager who…

I accuse YOU, jimmySixDOF!! That name gave you away - it's obviously autogenerated. And using “u” for “you” in an otherwise perfect post, just the kind of mistake a memory-free algorithm would make. UNMASK THE DEVIANT!

Re: Spinning Up in Deep RL

#32

Post by plants »

Asking for the benefit of me and others since this is on the front page now - are there any resources this comprehensive for any other field of study? This guide is amazing and I've failed to find anything else like it. I was specifically interested in biotech (from the perspective of a software developer, i.e. practically zero biology background), but will take what I can get

Re: Spinning Up in Deep RL

#33

Post by thewarrior »

Davidzheng wrote: post #8
colordrops wrote: post #3

Earlier quoted context omitted.

I assume this comment is generated? The link is a standard Sphinx doc.

If that comment is generated, I will quit my current job and work full time on AI. I don't believe it.

AI is now good enough to generate comments like that so you probably should :)

Re: Spinning Up in Deep RL

#34

Post by infimum »

GnarlyWhale wrote: post #18

Plug for the RL specialization out of the University of Alberta, hosted on coursera: https://www.coursera.org/specializations/reinforcement-learn... All courses in the specialization are free to audit. For those unaware, the university of Alberta is Rich Sutton's home institution, and he approves of and promotes the course.

Currently on course 2/4 in the series and it's great. Every week starts with a reading assignment from the RL book followed by a series of videos (re-)explaining stuff. The videos themselves are very nicely structured, with clear outlook and summary at the start and end of them. Sutton himself appears in a couple of videos and there are other great guest lectures with interesting insights about applications.

Definitely a recommendation!

Re: Spinning Up in Deep RL

#35

Post by rytill »

amelius wrote: post #27
317070 wrote: post #17

Earlier quoted context omitted.

All the blogs posted by e.g. this user [0] were generated by GPT-3. [1] Some of those reached the top of HN. That comment indeed looks a lot like it is generated. It has correlated a bunch of words, but it did not understand that the link between UI and AI is tenuous. It is probably one of the few comments where it is so glaringly obvious. There are likely a lot more comments around which are generated but which went…

Isn't gpt3-generated prose always seeded by some words or sentences? I'm curious what the poster used as seed, and why/if they chose to focus on UI? Would it be possible to use gpt3 to "beautify" existing prose without changing its meaning? Now that would be useful!

The prompt design likely has as input the HN title, and potentially some other metadata, but not necessarily the first few words of the comment.

Re: Spinning Up in Deep RL

#36

Post by randomsearch »

_5659 wrote: post #2

"Pray, who is the candidate's tailor?" -Hilbert Who is responsible for OpenAI's UI/UX design? It is immaculate and should be the standard for the community. I'm always dazzled by the impeccable standards of OpenAI with regards to tone, presentation, accessibility. The documentation is both familiar but distinct, an impressive achievement! I have my own personal qualms on OpenAI's ethics and virtues but am nevertheles…

‪It seems that the greatest achievement of GPT-3 will be to destroy HN, as more and more nerds “hilariously” cherry pick generated content and post it, gradually drowning all signal in a swamp of ever so slightly incoherent noise. ‬

Re: Spinning Up in Deep RL

#37

Post by unoti »

plants wrote: post #32

Asking for the benefit of me and others since this is on the front page now - are there any resources this comprehensive for any other field of study? This guide is amazing and I've failed to find anything else like it. I was specifically interested in biotech (from the perspective of a software developer, i.e. practically zero biology background), but will take what I can get

> Are there any resources this comprehensive for any other field of study? ... I was specifically interested in biotech

I recommend the FastAI course on deep learning. Several of their lectures relate to things their students have done in biotech and medical. The main lecturer Jeremy Howard has worked for years at the crossroads of medicinal technology and AI, and routinely discusses this.

The full fastai course is here[1] and free. Here is a blog post and associated video[2] as an example of fastai incorporating biotech into their work. In this example they use AI to upsample the resolution and quality of microscopes.

[1] https://www.fast.ai/

[2] https://www.fast.ai/2019/05/03/decrappify/

Re: Spinning Up in Deep RL

#39

Post by 6gvONxR4sf7o »

StavrosK wrote: post #22
colordrops wrote: post #3

Earlier quoted context omitted.

I assume this comment is generated? The link is a standard Sphinx doc.

I wonder if the fact that we now can't trust anything we read is good or bad. Maybe it'll lead to critically thinking about everything.

I suspect it's bad. Any cognitive dissonance and disagreement can be hand waved away as bots, rather than approached critically.

Ever since the 2016 foreign-meddling-in-the-election news, I've see people commenting that there must be tons of russian bots/shills/astroturfers/etc in comments where I see genuine disagreement. I'm sure there are both, but I suspect the dismissal of "'people/opinions' that disagree with me aren't real people/opinions" is more common than the actual act of fake commenting.

Re: Spinning Up in Deep RL

#40

Post by arthurcolle »

Davidzheng wrote: post #8
colordrops wrote: post #3

Earlier quoted context omitted.

I assume this comment is generated? The link is a standard Sphinx doc.

If that comment is generated, I will quit my current job and work full time on AI. I don't believe it.

https://www.youtube.com/watch?v=TxHITqC5rxE
Post reply on HN