| Tweetovi |
|
noahtren
@noahtren
|
14 h |
|
not quite solved in all domains, but it does feel close. Meena appears to be very impressive twitter.com/quocleix/statu…
|
||
|
|
||
|
noahtren
@noahtren
|
5. velj |
|
right, I'm hoping this rule would just be applied in situations where a doctored video is viral and has been debunked by a human. offloading to AI fully would be problematic
|
||
|
|
||
| noahtren proslijedio/la je tweet | ||
|
Maxim @ Config
@round
|
4. velj |
|
More programming should be like this. pic.twitter.com/Ek9wmXPWja
|
||
|
|
||
|
noahtren
@noahtren
|
4. velj |
|
I'm getting more sympathetic to the idea that malicious synthetic media should be a legitimate crime, but I'm open to arguments coming from the other side too
my main intuition is that blacklisting is better than whitelisting
|
||
|
|
||
|
noahtren
@noahtren
|
4. velj |
|
I like the heuristic he suggests: decide on a paper that you want to understand fully, then slowly encode the dependencies with Anki
|
||
|
|
||
| noahtren proslijedio/la je tweet | ||
|
François Chollet
@fchollet
|
4. velj |
|
Modeling the statistical structure of language absent any context is a bit like modeling the latent space of all airplane cockpits. It will enable you to generate new realistic airplane cockpits via interpolation, but it misses the purpose & the broader context of this interface
|
||
|
|
||
|
noahtren
@noahtren
|
3. velj |
|
unfortunately languages are going to continue to come and go since nobody really knows what an ideal computer language looks like. there are always improvements to be made over past langs. the big breakthrough will be in "learnable programming" imo
|
||
|
|
||
|
noahtren
@noahtren
|
3. velj |
|
I agree about the problem, end user programming needs work. I hope to see or even contribute to a visual programming language in the near future
|
||
|
|
||
|
noahtren
@noahtren
|
3. velj |
|
I like thinking about this. Also a chance that the initial scenario was never true
|
||
|
|
||
|
noahtren
@noahtren
|
3. velj |
|
their autopilot is incredible, check out this talk youtu.be/oBklltKXtDE
I bet the hackathon would be fun even considering that they use pytorch 😉
|
||
|
|
||
|
noahtren
@noahtren
|
1. velj |
|
3d printing!
|
||
|
|
||
|
noahtren
@noahtren
|
1. velj |
|
wow, this is super cool! will recommend to my friends that have given up on mining
|
||
|
|
||
|
noahtren
@noahtren
|
1. velj |
|
what are some good online courses that are very project-oriented? I learn best by doing, but I can't think of any accessible starter projects in what I want to learn (additive manufacturing and synthetic bio). I'm thinking something like the format of nand2tetris
|
||
|
|
||
|
noahtren
@noahtren
|
31. sij |
|
Cooperative Communication Networks can learn robust *and* human-readable representations. They could be used to help visualize a variety of complex problems. Really exciting to be working on this! twitter.com/advadnoun/stat…
|
||
|
|
||
|
noahtren
@noahtren
|
27. sij |
|
I would push back a bit and say that a graphing calculator's layout can be hard to navigate to a beginner -- each button has 3 modes to learn, and the contents of different tabs aren't obvious. but I agree that a REPL isn't the best solution
|
||
|
|
||
|
noahtren
@noahtren
|
27. sij |
|
"easy peasy" pic.twitter.com/USxr2eBPkW
|
||
|
|
||
|
noahtren
@noahtren
|
23. sij |
|
just got an assignment to write about Turing's imitation game. thinking about using Write With Transformer from @huggingface to help me write it, but not sure if it would help or hurt my argument 😛
|
||
|
|
||
|
noahtren
@noahtren
|
22. sij |
|
right?! I'm increasingly thinking that deep neural networks can squeeze representations into all kinds of mediums, given the right setup and enough time.
|
||
|
|
||
|
noahtren
@noahtren
|
22. sij |
|
I think I see some early code for some adversarial networks -- can't wait to see the outcome. Neat code, I like the variables for what the neural network is "saying" vs. "thinking" -- a great way to describe the difference between a signal and a message 😁 pic.twitter.com/HPTnArGoN6
|
||
|
|
||
|
noahtren
@noahtren
|
22. sij |
|
this is really neat, the rectangular size constraint also makes the results more more letter-like. would love to see the code 😃
|
||
|
|
||