Hacker News Reader

Comment by mark_l_watson | Hacker News Reader

I have mixed feelings about Gary Marcus. I enjoyed reading Rebooting AI that he wrote with Ernest Davis, and he makes some valid points in this article.

However, I think he ignores some practical use cases. I am not a good example since I am retired (I limit myself to about 6 to 8 hours a week consulting, and I am always working on writing a book) but I feel that I am at least 25% more efficient when using tools like GitHub Copilot integrated into Emacs and using Bing+ChatGPT or Bard for bouncing ideas off of, and sometimes for search. I find that if I carefully express an idea that I am thinking about that I usually get something at least interesting to think about and sometime very useful.

I am excited by research on hybrid approaches to AGI, but also excited by what we have right now with OpenAI and Hugging Face APIs and models that can be self hosted.

View on HN

Do you mind reflecting a bit on your use of Copilot? I've been trying it out, but I haven't found it to be particularly helpful.

I really find it to be more annoying than helpful. The mental burden of figuring out what the code is actually doing when a large chunk appears is exhausting, and it leaves me with a false level of understanding similar to the feeling of competency you get when you type out a tutorial's examples.

Underwhelming is how I'd describe my experience with ChatGPT too. There are so many people making claims of ridiculously improved efficiency, that I'm really unsure if it's me or not.

I used it for about a year with VSCode, then integrated it into Emacs. I easily ignore completions I don’t need.

I meant more “what are you actually completing?” And “how much?” I haven’t found the completions to be particularly helpful.

For instance, I’m often fighting incorrect array indices and slices, pulling out magic numbers into variables, decoding some one-liner completion, or figuring out what’s usable and what I need to cut out and replace in a larger block.

What’s really struck me is how much I really want Agda style hole-filling completion. I want to just be able to type a variable name and have it destructure cases for me. That happened a few times, and it was really nice. I’d forgotten how nice it was to be able to do that in Agda. I want that everywhere.

Also, just noticed who you were, I really enjoyed some of your Lisp books.

For Python, Common Lisp (that we both enjoy!), and a few other languages, I often get an entire function generated. If I ask for a function to make a SPARQL query to DBPedia, for example, it often generates valid SPARQL and code. I also ignore a lot of generated code.

Reply on news.ycombinator.com