AI and Machine Learning

Knowledge at Wharton

Ask about Knowledge at Wharton

Episode Description

📂 Technology

Read the full transcriptHide the full transcript
  1. we're speaking today with Justin got Schlick who leads the Machine programming research team at Intel labs
  2. the newly formed research group focuses on the promise of machine programming which is a fusion of machine learning
  3. formal methods programming languages compilers and computer systems Justin welcome to knowledge at wharton thank
  4. you so much for being with us here today wonderful thank you for having me McCool
  5. so I just read that description of what machine programming is but I think that you know given all the buzz around AI a
  6. lot of people are familiar with machine learning but most of them like me don't have a clue what machine programming
  7. means perhaps you could explain the difference between the two certainly yeah so at the very highest level
  8. machine learning can be considered within the subset of artificial intelligence and there's many different
  9. types of machine learning techniques one of the most prominent right now are these things called deep neural networks
  10. and that's a lot of what people are using to make the tremendous progress that we're seeing over the last decade
  11. the machine programming is really the idea that we are trying to automate the development and maintenance of software
  12. so the fundamental difference between the two is that with machine programming you can kind of think of all of the
  13. field of machine learning being a subset of the field of machine programming but
  14. in addition to using machine learning techniques which are these approximate types of solutions we'll also use other
  15. things like formal program synthesis techniques that will give us mathematically proven correct pieces of
  16. software and then between those two points you can kind of think of those as a spectrum you have the approximate
  17. solutions here and the precise solutions here and then there's a fusion of a number of different ways that you can
  18. combine these and every one of these things essentially is a part of the bigger landscape of machine programming
  19. so if I understood you right machine programming is when you create software that that can create more software right
  20. how would that happen and I wonder if you could give us a couple of examples just to help our audience understand
  21. this yeah so the idea of creating software that creates its own software is really the core idea between or
  22. inside of machine programming and a couple examples of that is we recently built a system using genetic algorithms
  23. and what it does is it'll allow you to take certain input output examples and then by running through a number of
  24. iterations we call them evolutions in the genic algorithm space it will then automatically synthesize the program
  25. that will match the input and output you do this sort of in the training phase and then it will take new input-output
  26. examples that it's never seen before and then generate these new particular types
  27. of programs so that's like one example that you might have in the space of machine programming and you would think
  28. about the impact that machine programming might have on different industries which industries do you think
  29. are likely to be affected most by this and over what period of time yeah this so this is a fantastic question and one
  30. that could require a very long response but I'll try to keep it slightly abbreviated at the highest level one
  31. could imagine that any of the industries that are predominantly based in software
  32. are going to benefit this benefit from this tremendously there was a recent survey that was done in earlier 2019
  33. that showed I think we have something like half a million computer scientist positions that are open so these are
  34. programming positions in industry that we need to fill but we're only producing roughly 10% of the actual programmers to
  35. fill those roles so what we're having in the software industry is essentially a bottleneck of supply if we can start to
  36. automate some of the simple tasks you know reading in a file parsing data helping us automate that
  37. software development testing this will I think tremendously accelerates the rate
  38. at which software is being developed so I would say that that's probably the first very obvious place the other area
  39. that I think is going to be impacted tremendously by this are autonomous systems in most of the spaces in
  40. autonomous systems a core ingredient of those systems is software so for example
  41. if one were to think about autonomous vehicles a large part of what's holding us back from getting to level 4 level 5
  42. autonomy which is the point where the car can essentially handle all of the nuance behaviors of driving in downtown
  43. Philly or something of that nature a big bottleneck of that is really the implementation and the algorithms of the
  44. machine learning systems if we can automatically construct those these autonomous systems will also accelerate
  45. in their advancement I'd like to come back in a little bit to the question about autonomous vehicles and the impact
  46. on the auto industry but given the fact that a lot of our audience is in the financial services industry I wonder if
  47. we could go a little deep into that so I mean I know that AI has made quite a significant impact for example in areas
  48. like fraud detection right do you think machine programming can also have a major impact there and if so what what
  49. might that look like absolutely this is a fantastic question and as I was mentioning earlier with machine learning
  50. systems their foundation is essentially learning through statistical analysis in
  51. some sense this makes them probabilistic that they are getting us close to the the right answer but there's in many
  52. cases we're not guaranteed that we'll have the right answer when we think about machine programming we go back to
  53. that spectrum of how we have probabilistic to very precise solutions it's my belief that for example in the
  54. financial sector there are certain cases where probabilistic solutions aren't sufficient so one might speculate that
  55. as you're doing some sort of financial transaction having the probability that oh i sort of
  56. been rounding off the sense right you know i'm close enough probably isn't sufficient if those transactions are
  57. happening billions of times a day in that case we need a more precise solution and this is one of the areas
  58. that i think you could use machine programming an interesting coming back to the other industry that you mentioned
  59. and the auto industry what kind of impact do you think the machine programming will have on the whole drive
  60. towards autonomy you i think you started talking about that in the context of philadelphia yeah but i wonder if you
  61. could go a little more deep into what that might look like for sure so as i was mentioning earlier
  62. we recently built a system that is using this dis genetic algorithm to automatically construct programs what i
  63. didn't mention is one of the pieces that's part of genetic algorithm just this thing called a fitness function the
  64. fitness function is essentially you can think of it as a way that you grade the accuracy of the programs or the results
  65. that the genetic algorithm is giving so genic algorithm produces a result and the fitness function says you get a b or
  66. you get an A historically though fitness functions have been written by humans and not just any human really expert
  67. machine learning humans oftentimes what we find is the complexity of the problem
  68. you're trying to solve is directly related to the complexity of the fitness function so one could naturally infer
  69. then why would you write the fitness function just solve the problem yourself so we took a look at this and what we
  70. did is we figured out a way using machine learning that we could automatically create the fitness
  71. function without a human involved so now going back to your question if you think
  72. about this type of thing in the autonomous vehicle space one of the things that's holding us back is the
  73. advancement of ML systems and historically the advancements that we've had with ml systems have been through
  74. humans creating them but if we use machine programming one could imagine like we have with the genetic algorithm
  75. solution that the machine can actually start to invent it's own machine learning systems that
  76. will then accelerate the progress of these autonomous systems so what are the implications of that well one of the
  77. things that I've heard about that's holding back autonomous systems as you are the autonomous vehicles is the fact
  78. that it might be too late to too far for the system to make a certain decision yeah and and you because you don't want
  79. to actually hit something right you you you you probably need software that can predict what's about to happen before it
  80. actually happens is that one of the issues right here absolutely right so this is tremendous insight and and
  81. actually we had a nurbs paper nerps is one of the leading research conferences in machine learning we had a nurbs paper
  82. in 2018 that tried to start to address this problem so historically what you're describing here is the space of anomaly
  83. detection so the Antonidas vehicle space when we think about these various behaviors we
  84. think this is an anomaly and in particular that's a time series anomaly so for example you're trying to prevent
  85. this vehicle from colliding with this other vehicle or make sure it doesn't hit a pedestrian and as you pointed out
  86. it's too late if you already have the event happened to you know detect it so what we did in order to address this is
  87. we recreated the mathematical foundation for anomaly detection specifically for time series and so with this now what
  88. our hope is is that the community will adopt the new mathematical foundation we've created and then they can apply
  89. this for time series and Omni detectors which will start to address those types of problems so and machine programming
  90. helps at all this absolutely so in the context of autonomous vehicles you could think of using this mathematical
  91. foundation to better predict these anomalies but when you think about machine programming or you think perming
  92. in general many of the problems we're seeing today with software is we have these correctness bugs we have security
  93. bugs we have these privacy violations all of these things in some sense are time-series in nature
  94. program is really just a sequence of instructions one after another so if you take that mathematical foundation you
  95. can also apply it in the space of machine programming which is exactly what we're doing well one thing I'm
  96. curious about is that machine programming like a lot of other areas of AI has been around since the 1950s right
  97. what's behind you know the sudden interest in machine programming now why is it picking up in such a big way and
  98. why is Intel you know so interested in sort of investing it in in it in a big way this is a fantastic question and
  99. I'll try to break it down to those two pieces first address why we're seeing the you know the resurgence of this
  100. because it has been around since the 1950s and then why is Intel so interested if we look at why it's taking
  101. off today I would say principally there's two reasons the first is I believe we're at an inflection point and
  102. the second is I believe my colleagues and I at Intel Labs and at MIT we've made an important sort of observation
  103. and how to think about the future of machine programming so as far as the inflection point goes we believe there's
  104. really or my view is really that there's three things that have created this the
  105. first is we have tremendous advances in algorithms in machine learning and in formal methods things that didn't exist
  106. say 12 months ago potentially are fundamental to the advancement of machine programming the second is we
  107. have tremendous advances in compute today as the recent Turing Award winners Dave Patterson and John Hennessy how are
  108. pointing out is we're living in sort of what they call the Golden Age of computing which they refer to as they
  109. call them domain-specific architectures that for a long time it was really just the CPU but now we're seeing based on
  110. the advances were having a machine learning in other areas we have these accelerators that are specific to these
  111. domains and so it's creating a tremendous opportunity for acceleration of machine learning and formal methods that
  112. wasn't possible and then the third piece is the abundance of big and dense data for example there is a repository that's
  113. called github and github basically as a place where people store their software and what we've seen by looking at github
  114. is back in 2008 I think it had roughly 33,000 repositories 2009 when I looked at it earlier this summer I think it was
  115. somewhere around over 200 million which is yeah it's it's a tremendous growth it's it's actually nearly a four order
  116. of magnitude growth in a decade and that kind of of growth and data as you probably know data really drives a lot
  117. of these machine learning systems so this is created essentially a vehicle in which we can start to explore this space
  118. so that's the inflection point but now goo the other point of the thing that's Intel and I think MIT observed is
  119. fundamentally what we're seeing is the way we've historically done programming we think is flawed that there's
  120. essentially a blurring of the programmers intention with these algorithms and with the system level
  121. details what we really want to do as we move forward is we want the programmer to just specify his or her intention
  122. that you you want to create a program that will tell you where the nearest Starbucks is and you just say computer
  123. create a program that will always notify me when I'm near Starbucks and then the
  124. computer handles all the details of the algorithm to implement it understands how to translate that to work on the
  125. hardware that's on your cell phone or in a data center that type of thing so that
  126. those are the two pieces that we think really are creating this opportunity for tremendous growth in machine programming
  127. now to your second point about why is this interesting to Intel until obviously is very interested in advances
  128. in hardware and me being at Intel for about a decade now one thing that I've seen which is really exciting
  129. is Intel really used to be just a CPU company and we're not today today the heterogeneous hardware landscape that we
  130. have at Intel is enormous we have neural network processors we have neuromorphic processors we have
  131. GPUs we have a variety of accelerators we have FPGAs and we have a ton of CPUs the problem though is programming these
  132. things that we can have all this tremendous harder but how can we possibly expect that the average
  133. developer can program this and this is really why machine programming is essential to Intel as Intel understands
  134. that with this new heterogeneous Hardware landscape that really is required to advance all of the
  135. technology that we're seeing we need a way that it's simple enough for the average programmer harness this
  136. massive amount of heterogeneous compute it sounds amazing the ISO since he was speaking about the work that you did
  137. with MIT I understand that you wrote a paper called the three pillars of machine programming mm-hm
  138. some time ago about some of these concepts and I was wondering if you could share some of the main insights
  139. from that and how they relate to some of the things we're talking about certainly
  140. yeah so back in I think it was 2017 a few of us from Intel labs teamed up with several people at MIT and we came up
  141. with this vision of what if we did this thing called machine programming what would the landscape look like and the
  142. main reason for this is we were seeing in these research venues that people were starting to explore machine
  143. programming but they were a bit disorganized that there wasn't structure around the way we were thinking and so
  144. the paper that we wrote the three pillars of machine programming is essentially a road map on how we want to
  145. express and explore the research space there are three pillars intention invention and adaptation the intention
  146. pillar is really what we would think of as the programmer is do in the future I don't really call these
  147. people programmers I call them software creators because at the end of the day our our blue sky vision is these folks
  148. won't write a single line of code they will express their intention either through natural language gestures visual
  149. diagrams whatever is best for them and and for those hardcore programmers out there they can still write all the code
  150. that they want so that's the intention pillar the invention pillar is it then takes the programmers or the software
  151. creators intention and then translates that into the actual software these are the algorithms the data structure is
  152. that type of thing once that's established then that work gets handoff to the adaptation pillar the adaptation
  153. pillar then takes that code and then figures out ok what is the software and hardware ecosystem look like for this
  154. particular program how do we need to augment it to make it run efficiently securely correctly and then in the
  155. machine learning context accurately now in addition to Intel I'm sure there are other companies that are also working on
  156. machine programming and I wonder if there are any companies with whom you collaborate whose work you could talk
  157. about just to explore how this field is evolving absolutely so yeah we have many
  158. collaborators in industry as well as academia and some of our industrial partners that are looking into this are
  159. Microsoft and Facebook so Microsoft's they have a wonderful gentleman over there submit Gulani who's seen in in
  160. many people's eyes is one of the founders of formal program synthesis and he actually has developed the system
  161. inside of Excel that will automatically figure out what the users intent is they
  162. call this flash fill so this is a good concrete example of real-world evidence that this is not just a research toy you
  163. can actually build this into real products so Microsoft is deeply interested in this another company is
  164. Facebook so Facebook is actually doing tremendous work in this space they recently published a paper about
  165. a system called aroma and what aroma does is essentially works along the same lines of the three pillars it's
  166. principally focused on trying to help with the intention that a programmer has an intention of trying to write some
  167. code and doesn't quite know exactly how to write that code the aroma system then will take a little
  168. bit of that code and do an analysis over a very large database and then send the
  169. user back is this what you meant and it's sort of a human-in-the-loop machine learning approximate solution that's
  170. sort of good early evidence that there's a lot of while while we think of the space machine programming as being a
  171. very long journey there's things that we can be doing today in industry that could be extremely valuable
  172. that sounds pretty remarkable again know you spoke about several companies which
  173. countries do you think are making progress that you find impressive in the area of machine programming in general
  174. in AI I've heard that China is you know advancing in leaps and bounds could you talk about you know what's happening in
  175. other parts of the world and what are some of the things that you are paying attention to absolutely
  176. so as you pointed out China is doing tremendous things one of the things that they're doing is they have a very strong
  177. sort of governmental infrastructural support for AI and it's my belief that the u.s. also has this but maybe not to
  178. the level that China does it's something that I think as a country we probably need to be a little bit more aggressive
  179. and progressive about there's also a lot of involvement and advances that are happening in Europe and that's also tied
  180. in both with their academic schools they have very strong ml leaders and academia
  181. and then also the vision that they have through their governmental infrastructure which European country is
  182. you think are doing the most interesting work that that's a great question off the top of my head you know Germany is
  183. actually doing some really tremendous stuff as one might imagine part of that has to do with the fact that
  184. they've been deeply involved in autonomous or vehicles and the natural evolution is autonomous vehicles and
  185. then the byproduct of that is deep engagement in AI and machine learning no D which innovations and machine
  186. programming do you think most promising and where do you think the next breakthroughs will occur in the
  187. immediate future yeah so this is this is a really fascinating question and as I was mentioning before there is a lot of
  188. low-hanging fruit where we can make advances and we can build things like aroma or flash fill that are very useful
  189. but there are some core challenges that at least with the folks that I'm interacting with that places like
  190. Stanford and MIT and Google and deeply within Intel labs that we don't quite have the answer to the first is the
  191. structural representation of intention so what I mean by this is oftentimes when we're writing code
  192. the programmers intention is diffused across of the code what we really want to be able to do is understand how to
  193. properly represent the user's intention and we don't quite have this there's a lot of advances that we've made
  194. historically with things like compilers and static analysis tools that create different sort of graphical or tree
  195. structures but when we've tried to apply these in the space of machine programming they don't quite fit that we
  196. can sort of you know push the you know square peg in the round hole but it's not the right match so I didn't tell
  197. we're thinking about this thing that we're sort of roughly calling the abstract semantic graph and the idea
  198. here is this structure whatever this is that we don't quite understand will be some sort of graphical representation of
  199. the semantics essentially the intention of what the user wants once we figure out how to build this thing my belief is
  200. the field of machine perming will see a tremendous spike of growth so a lot of people are working on this I'm working
  201. with collaborators both in industry and then in academia folks at Penn Berkeley MIT we're all
  202. thinking deeply about this hopefully we'll be able to figure out this this abstract semantic graph soon and until
  203. we do I think that we'll just sort of work with the maybe not perfect solutions and try to you know edge our
  204. way forward so if you figure it out what might some of the implications be so some of the implications will be the
  205. programs that we'll be able to generate are likely to be orders of magnitude more complex than the ones that we can
  206. create today for example in the space of formal program synthesis or approximate
  207. solutions for machine programming we may be restricted to let's say programs that
  208. are up to maybe a hundred instructions or less if we figure out how to build this abstract semantic graph it's my
  209. belief that we will move from hundreds to thousands potentially millions of lines of code that so the implications
  210. of this thing they're enormous so when any new technology comes along especially a machine learning or as you
  211. described machine programming very often technologists have to justify these investments to the CFO or to the CA CEO
  212. not just in terms of this is very cool technology but right this fits in with the ROI of where the business wants to
  213. go or order fits in with the business strategy what are some of the metrics that you think about in terms of what's
  214. the ROI in measuring the ROI of machine programming right this is a great question and of course as the leader of
  215. the machine programming research group at Intel it's my job not only to work on the research but then also justify its
  216. business value as you pointed out and one of the things that you you might know is Intel's very interested in
  217. performance but we're not just interested in Hardware performance we're also interested in software performance
  218. so one could imagine that if you have a programmer that's writing code that's slow
  219. they might blame the Intel processors is being slow even though the problem is not the processor it's actually the
  220. software one of the promises of machine programming and we're seeing early evidence of this is that the code we can
  221. generate through these automated methods will be superhuman in their performance
  222. correctness security so on and so forth one concrete example of that is one of my colleagues Andrew Adams
  223. Jonathan Regan Kelly cave on photo Holly and Diaz are folks from MIT Stanford and
  224. Facebook that were actually I think Andrew Adams just pivoted to Adobe research they have built a system called
  225. halide it's a programming language that separates out the programmers intention from the actual scheduling of that
  226. intention and in their recent paper this year that was published or I think in June they've shown for the first time
  227. that the world's foremost experts in this programming language can't compete with the machine that the machine is
  228. producing code now that is regularly more efficient and I think it's by I'm gonna be I'm just gonna guess here by at
  229. least 50% it might be upwards of you know a hundred percent faster and this is the first time in the decade that
  230. they've been working in halide that they've been able to achieve this but so this gives us promise that if we can do
  231. it in halide maybe we can generalize this and start to improve the efficiency of code everywhere this is really
  232. important to Intel because obviously we want everyone software to run as efficiently as possible and we don't
  233. want people to mistakenly believe that our hardware slow when actually the problem is somewhere else no I I I hear
  234. you and it actually reminds me of a broader concern that I have often heard about AI which is that as a lot of
  235. automation begins to take place and AI systems get implemented that the impact of jobs could be considerable so for
  236. example but autonomous trucks it has been a fear that lots of truck drivers could be losing their jobs if
  237. you know autonomous vehicle stopped hauling you know goods across the highways so do you think that there is a
  238. risk that if machine programming takes off that the same thing could happen to software programmer jobs and that this
  239. this is something that the industry should be concerned about right this is an excellent question and one that I'm
  240. asked quite often my my honest opinion is actually the inverse will happen is that through machine programming we will
  241. create many jobs perhaps millions or tens of millions of jobs and the reasoning is actually very simple right
  242. now we have a global population in the billions yet the programmer pool today is a very small percentage I don't know
  243. the exact percentage but I think that it's roughly around like 1% of the global population with machine
  244. programming what we are are trying to achieve is enable the entire global population to create software for
  245. example my mother she's incredible you know entrepreneur she's created several businesses and has just done fantastic
  246. but she's not a programmer so the entire world of software is closed off to her and in fact this is one of the reasons
  247. that I became so compelled is I see someone like her who's wildly creative she has some amazing ideas but because
  248. software's closed off those ideas never get realized and hopefully with machine programming with this intentionality
  249. that we're discussing earlier this will this will create tens hundreds of millions of jobs it'll also keep the
  250. programmers that we have today employed because there is work to do on building these very complex systems and as we
  251. expand intentionality we're going to require those people those what we call it Intel those ninjas to be ensuring all
  252. the subsystems that are part of those three pillars are advancing appropriately so since we were talking
  253. about these advice consequences it reminded me of a conversation almost 15 years ago with
  254. Andy Grove the former CEO of Intel whom we had interviewed in 2004 and and he once said that for every metric there
  255. should be another paired metric that addresses the adverse consequences of the first so as you were thinking about
  256. some of the metrics that you would use to measure the success or the ROI yeah off of machine programming what would be
  257. some of the adverse consequences of machine programming and what metrics would you use just to keep an eye to
  258. make sure things don't get out of control I'm really glad you asked this question and on top of that before I
  259. answer I just want to say I'm a huge fan of Andy Grove it's wonderful to be at a
  260. company with such strong legacy of leadership and you know we see the impact that Andy has had even today that
  261. the company is really trying to follow a lot of his principles I would agree with
  262. you wholeheartedly and in fact in a book that we wrote in 2004 that knowledge at
  263. Wharton wrote he was identified as the top leader among 25 leaders in the past 25 years oh that's fantastic
  264. yeah I never got the chance to work with him personally but I know people that have and from everything I hear he was
  265. not only a tremendous leader but also tremendous technologist which is sort of a very rare combination but going back
  266. to your question about the adverse consequences we actually talked about this a little bit in our three pillars
  267. paper and this is part of the reason why we we wrote this paper is that what we were seeing in some cases of advances is
  268. there would be research for example one of my colleagues that I'm very fond of Alvin Chung he's a professor at Berkeley
  269. and he's doing this work called verified lifting and verified lifting essentially
  270. uses formal program synthesis techniques to lift code from one programming language and then drop it down into
  271. another programming language this is wildly useful for legacy systems that can't be maintained because we don't
  272. have a programmer supply we can lift that code out put it in language where we have lots of
  273. programmers however one of the things we noticed and I've discussed this with Alvin so he will probably not be shocked
  274. when I mention this is that there's a potential byproduct of that lifting that can reduce intentionality so for example
  275. his work we would say principally falls in you know the invention and then the adaptation based on how that code is
  276. transformed the intentionality of that code could be reduced for example things like variable names function names
  277. things that are really important to programmers may not map properly to the new structure so as we're making forward
  278. progress in machine programming what we've asked the community to do is think of the context of the three pillars and
  279. then try to understand are you inadvertently hurting another pillar and if you are clarify that so we understand
  280. that this is another thing that we now need to advance now since you mentioned you know some of the academic
  281. collaborations I was I know that you spoke at Penn that did precise event last week and I was wondering if we
  282. could end by talking a little bit about what kind of work you are planning to do
  283. here at Penn oh yeah so I'm yeah very delighted that you asked this question and I'm really happy to be here
  284. I had the honor of giving this talk at the precise industry day which was over sold out I think people were sitting on
  285. the floor it was just very well attended and rightfully so the lot of the thought
  286. leaders in the space of computer science and formal methods in machine learning are part of the precise center recently
  287. I accepted invitation to help chair the technologists regroup for precise and also act as their executive director for
  288. artificial intelligence my role with precise and with Penn actually I think is twofold the first is with precise
  289. they have a very strong sort of technical Horsham of industry collaborators and what I would like to do is ensure that
  290. all of the industrial partners are working in a very complementary way that we understand what the core challenges
  291. are and that we're not working in a way that's overlapping duplicating effort so
  292. that's one part the other part that's really important to me is right now we have sort of a lack of machine
  293. programming engineers and researchers in fact there's very few of us which makes
  294. sense because the field even though it's been around since the 50s it's had struggles to get to the point where it
  295. is today so what we're working on with Penn and other academic Institute's is to start
  296. to incorporate curriculum changes and get our undergrads get our grad students more familiar with it and then also
  297. generate the new leading minds through the PhD programs that are then going to drive the research they're happening
  298. both in academia and in the industrial labs that sounds wonderful and Justin thank you so much for taking the time to
  299. explain all these things to us it's wonderful to meet you and very happy to have you here at knowledge at Wharton
  300. yeah it's been my pleasure thank you so much for having me for more insight from
  301. knowledge at Wharton please visit knowledge Wharton UPenn edu [Music]

Brief Summary

Justin Gottschlich discusses machine programming's role in automating software development and its implications for various industries, including finance and autonomous vehicles.

Key points

  • Understanding Machine Programming. Justin explains the difference between machine programming and machine learning.
  • Impact on Industries. Machine programming could revolutionize industries reliant on software development.
  • The Three Pillars of Machine Programming. A roadmap for machine programming focusing on intention, invention, and adaptation.
  • China's AI Advancements. China is making tremendous strides in AI, supported by strong governmental infrastructure.
  • The Future of Machine Programming. The development of an abstract semantic graph could revolutionize machine programming.
  • Job Creation Through Automation. Machine programming may create millions of new jobs rather than eliminate them.

Episode highlights

Tension

45/ 100Some tension

Related episodes