I loved Openai's codex JavaScript game making live demo(1) where they actually created a fully functioning game in JavaScript using just plain old english. Kind of changed my whole view about programming and it's future. (1) [this video]
Live demo building a working JavaScript game from plain English.
Here's a pretty impressive demo. [this video] I think they said it handles something like 37% of requests. Btw, don't watch it if your worried at losing your job to a computer.
Impressive demo of Codex turning requests into working code.
Really depends on the domain and the engine. OpenAI code generation is staggering ( [this video] ), its summarization and classification is still very much a work in progress.
Yea the code on the top level is very cartoonish and almost comical. But the model can definitely produce running code. Chat GPT is a similar model that runs codex, see the demo here: [this video] One point I try to get across is that once you drill deep enough into the call stack of implementing subroutines, you will start just asking it to produce code not explicitly related to the top level mission of overthrowing humanity.
Fair point on sensationalism, I think it's a useful hook to get folks reading and talking. There is a "Nuance" section at the bottom where I qualify most of the rah rah language. That being said, I disagree that it is that far from actually working. Check out the codex demo here: [this video] This is a year old and we've made a lot of progress since then. The model is certainly capable of writing non pseudo-code, although I started hitting rate limits before I got it all the way there in my example. Edit (typos)
Codex demo supporting claim models can write real code.
That's a rather silly strawman. OpenAI demonstrated Codex - a version of GPT-3 which could write Python and JS code - in 2021, only a year after the first GPT-3 release. Here's a demo of Codex doing MS Word tasks using Python code: [link] Live coding demo: [this video] There's also a demo of doing some data processing using Codex. The idea of using LLM to write code is rater obvious, and many people talked about it around GPT-3 or even GPT-2 release. People know that many logic tasks require search and it's rather silly to use LLM to do that. If it can generate any text it can generate Prolog code or a specification for SAT solver, and then dedicated efficient tool can handle the computation. Gary Marcus is so detached from actual research that he might have genuinely missed the 2021 version of Codex. So he might truly believe that they added Python interpreter "quietly", and it's not the big announcement of 2021. This guy is known as a clown in the industry, and for a very good reason... If he was an actual researcher he would have jumped on the opportunity to make an actual neurosymbolic demos when first language models were released - you don't actually need to wait GPT-3 to do that. But he preferred to relish in writing books claiming that the entire industry is wrong instead of actually building something.
Shows Codex live coding demo from 2021 as evidence LLMs writing code is old news.
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
6 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Citations, criticism and jokes
Read more