Same as code, the llm can generate vast amounts and it seems to work, but no one understands the documentation Claude Code, or other LLMs, produce. Essentially, garbage because, to make use of it you need to be able to understand it, usually at a cost (unquantified), and if only LLMs do then what is the point?
Yes, it is awesome. Funny we got this level of capability now and we all take it in our stride. Growing up in the 80's I loved futuristic scifi, feels like I am in it now. And even I am 'just' taking it in my stride.
What I am thinking is the way you make it 'keep going' and when you have people of the calibre of Tao doing it I kept thinking how many breakthroughs is he going to cause the LLM to find with his targetted questions :D Amazing that we have the privilege of witnessing a true expert in such a way question the LLM.
I am even tempted at this point to test Mistral, even though the signs say it lags behind quite far. I just wonder if that as a bottom bar is good enough.
The whole Anthropic/US administration/Fable guardrails/overpricing situation has been so frustrating for me and disruptive that I am really an inch away from just removing Claude Code/Codex (or any other US LLM) from my daily use.
I wonder how many others are feeling like I do at this whole situation?
Not very pro or anti BASIC but very pro your rationale, and love that you do what you do because it is fun and stimulating. I love reinventing wheels also, and, in fact, believe it is under appreciated just how useful it actually is. I'd encourage people to reinvent things for their own benefit, maybe you might end up building a better version of something, but more importantly you will possibly encourage, energise or inspire another to explore and learn.
This is potentially a inflection point for windows being the dominate OS. If Google, who now have Android working on desktop, and can market it well enough. Since half of the mobile users in world would be less afraid to try something they are familiar with on their phones.
Yes, I agree, and understand the point better. Totally a great thing if this can be made accessible to a wider audience and not expect them to do all the work to grok it, especially if there are easy/easier ways to bring it to a wider audience. The parentheses don't usually remain a problem after the initial bump, I had the same issue when I started clojure but after a short while it doesn't continue to be jarring. I think after about 90 minutes it just started to be "natural" perhaps that the wrong word, it was just something that was like ok after a bit and didn't notice too much.
I think the initial surface look makes scheme give a bit of an 'oh crap' response. But since minikanren is actually a small program and scheme doesn't really have syntax the language should be less of a problem than initial concerns might make one think. Grokking the actual logic in any language is going to be the bigger challenge. I guess I am trying to encourage just rolling with lisp if you can, but I totally get the initial reactions toward scheme though.
I don't know about other people's experience, but from mine, I see a lot (most) devs abstracting too early in the name of clean code. I guess engineers gonna engineer when simple boring repetition is sufficient and those premature abstraction are unnecessary.
Unfortunately, I don't feel confident humanity has the ability not to destroy the environment that sustains our life. We are simply too selfish, unable to adjust our thinking to new information sufficiently, lack compassion for others, and/or just don't care about things that don't affect us directly.
Pure functions, i.e. that are 1) idempotent 2) have all their arguments passed in 3) cause no side effects as a by product of evaluating the function are fundamental to functional programming.