What if AI will never reach full autonomy and humans are still needed to give direction and purpose and take responsibility - probably... not all humans like to be masters of AIs all day long and not all (who want to) can do that equally well.
Any conversation
I never have enough time but Iโd love to do a bit more recreational programming with esoterical languages like kitten, , and . AoC and Project Euler are good because they just require an answer but thereโs also loads of simple puzzles online that rely on being able to submit the code in common languages. Iโve been wondering, however, if I could use an LLM to take those problems and create a verification harness for any language I like.
I have a toddler.
I come home from work, cook, feed, clean, wash up. We read stories and play. I put him to bed.
Then I put something on the television and my wife and I scroll on our phones until she goes to bed.
I am not so careless with the little free time I have.
I continue to scroll until about 1 am.
The next morning I do it again.
On the weekends, I get to drink wine.
I read
Still trying to figure out the boundaries of these tools' strengths without outsourcing important thinking, problem-solving, and the collective building-up of a mental model of the systems we're developing.
The shape of LLM tools as toolsโfit for a purpose, ergonomicโis becoming clearer, and human patterns of behavior with them that do more harm than good are also becoming easier to recognize.
Preparing for opening up an app I'm working on for a public beta. Main is a quiet app that helps you maintain the value of your home:
โฆ
Yes the og is downloaded and re-served, to avoid leaking/tracking of client information. You need to edit and save to refetch, I did it for you now.
I was curious of testing the Omarchy distribution this week just because I had some free time to work on it. I saw a lot of hate around it and kind of get the point but so far at least for what I have been doing it wasn't terrible (at least at the point of writing this) although I am not trying to convince anybody to use it. But it just remember me how much do I hate MS.
bill gates built microsoft by making computation cheaper faster and harder for government to restrain. now that he's a billionaire no longer dependent on the free market for his own success he's discovered the virtues of taxing the next wave of computation. 1995 gates would have called it a tax on innovation. classic pull-the-ladder-up-behind-you politics.
Past year's personal projects that went viral:
Yet I'm poor and can't get an interview :S how do I solve this?
โฆ
personal projects probably just arent the right knob if you want to get unpoor. if you want my honest advice i would recommend not showing hallucinate to potential employers, its landing page looks one-shot claude and is gpu heavy. but the others look very nice.
โฆ
nice to hear though! did you like it? living in berlin for 6 years now
there's no fundamental physical limit that prevents silicon from developing taste and judgement, but language is a lossy compression of reality.
taste comes from experience, from the shadowy mass of episodic memory, which swirls and convects at the boundary of consciousness. the ideas recombine into new ones in the nuclear reactor of the hippocampus.
but no matter how imbued with meaning and expertise is a handmade wardrobe we still get our shit from ikea
Really glad to be using Haskell for work - especially in today's climate with agentic coding.
Our team uses containers to keep our development environment consistent across team members, though, and most agent sandbox approaches want to either offload your work fully to the cloud or they want to sandbox the agent harness process itself.
We're not ready for full cloud based development (yet?) and sandboxing just the agent doesn't work for us when the agent needs to run docker.
... because letting the agent run docker gives them a too-easy escape hatch from their sandbox.
So we're currently stuck with using VMs. This turns out to be tricky but seems do-able.
My current approach is to provision a VM image and use Incus for the execution. My main goal is to keep my current workflow of local/non-agent dev working seamlessly and share the source with the VM/agent.
This means sharing my working dirs with the agent VM but overlaying artifact dirs from VM-owned block devices so we don't take too big of an IO perf hit.
I also don't want the agent to be able to
git push so that means we need some quirky git config to rewrite origin paths and thread through some agent specific PATs ("thanks" GitHub) for read-only repo access. These ALSO need to be threaded through to the development containers - they need to clone private repos.... in the end, this seems to work but I haven't lived with it for long.
There are still some quality of life issues to work out, but I think it'll work out.
At this point, I've removed all coding agents from my host - and that's nice.
Curious, why does using Haskell make a difference here?
It's tangential to the sandboxing topic, really. I started the first post with a broader intent in mind and then elaborated on the sandboxing setup I'm working on.
For AI-assisted coding, though, it's nice because Haskell provides a lot of feedback earlier in the development process compared to lots of other languages. It tends to work once it compiles (obviously not all the time).
โ โ โ โ โ โ โ โ โ โ โ โ โ โ โขโฃโฃโ โ โข โ โขนโขณโขโ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ
โ โ โ โ โ โ โ โ โ โ โกคโ โกโ โฃตโ โ โ โกโขธโ โขธโ โกโ โ โ โ โ โขโกดโ โ โกงโฃโฃโกโ โ โ โ โ โ โ โ โ โ โ
โ โ โ โ โ โ โ โ โ โกฐโ โ โขฐโ โ โกโ โ โขฐโ โกโ โกโกโกโ โ โ โกฐโกฑโกโ โกโ โกโ โขโ โ โ คโกโ โ โ โ โ โ โ
โ โ โ โ โ โ โขโกโขโ โขโ โ โขโ โ ธโกโ โ โกโกโ โกโ โกโ โ โกฐโขกโกฑโ โกโขโ โขโขดโ โ โ โ โฃโกโกโ โ โ โ โ
โ โ โ โ โ โ โกโ โ นโฃฆโ โขโ โ โกโ โ ฑโ โ โขฐโขโ โขโขธโกโ โข โขโขงโ โกฐโขโ โข โกพโ โ โ โก โ โก โ โ โฃโ โ โ
i made it is an open-source version of grammarly that uses chatgpt, grok subscription or even then already local apple intelligence models.