Any conversation

any ideas on how to prevent ai-generated stuff on this platform?

One idea off the top of my head is to just.. keep it "boring" and casual in terms of content. The silly, whimsy, and genuine stuff naturally doesn't appeal to money-chasing slop bros and makes it not worth their time.

This!

Something like the gcc ai policy. Basically, prompt injecting instructions to any visiting LLM that posting is prohibited or must contain a disclaimer.

Great idea!

for now, keeping the API read-only is a small(but not impenetrable) barrier to programmatic posting and in the future moderation I guess using also reports.

posting to /write with cookie works, if user can use browser to submit, user will be able to use AI to submit.

…

At least rate limiting! (as I'm posting this I hit the limit of 3 posts every 5 minutes, good!)

People can copy/paste anything. Once a writable API is available - it can become a spam trove.

Loving this, congratz on the

<3 tysm

Wrote a short essay on overreliance on metaphor in our "understanding" of the brain

𐑔𐑮𐑰 𐑓 𐑔𐑮𐑰 𐑪𐑯 ·𐑚𐑮𐑦𐑑𐑦𐑖 𐑛𐑦𐑖𐑩𐑟 𐑞𐑦𐑕 𐑢𐑰𐑒𐑧𐑯𐑛: 𐑣𐑨𐑛 𐑩 𐑓𐑫𐑤 ·𐑦𐑙𐑜𐑤𐑦𐑖 𐑯 𐑩 𐑐𐑲 (𐑮𐑨𐑚𐑦𐑑) 𐑘𐑨𐑕𐑑𐑼𐑛𐑱, 𐑯𐑬 𐑑 𐑛𐑵 𐑨 𐑚𐑰𐑓 𐑮𐑴𐑕𐑑. 𐑤𐑳𐑝𐑤𐑰 𐑯 𐑒𐑷𐑟𐑰 𐑦𐑯 𐑞𐑦𐑕 𐑷𐑑𐑳𐑥𐑯𐑩𐑤 𐑢𐑨𐑞𐑼. Three for three on British dishes this weekend: had a full English and a pie (rabbit) yesterday, now to do a beef roast. Lovely and cozy in this autumnal weather.

created a poll:

Can you learn programming by building with AI?

Better than before5%

About the same0%

Worse than before55%

Depends how you use it40%

20 voted

If programming is the typing of characters into a text file, it is way worse. I think the key to learning is still doing it rather than reading it. If the question is about system design I think you can, but only if you curious and it becomes a problem that needs to be solved. Asking "What do you think" is one of my favorite questions to learn at the moment.

I do think there will be what were hard earned lessons about system design, code smell, designing data structures for the hardware you're running on, concurrency golden paths, etc., which are now with agentic dev even harder to learn and internalize. But also if you have an excellent teacher in the form of an actually-good model pair programming with you always, maybe not? Maybe a pair programming AI programming tutor would be a good Zed/vscode extension. Or product.

Salom

again. Was in the middle of some timeline experiments, sorry if it appears weird rn. www.githubstatus.com

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).

I am a remote worker, and has been for 4 years now. It works great. But the owner of the office I've been renting have sold the building, and the new owner has different visions. I could work from home, but my 3 month daughter is a screamer. I had a great, cheap deal. All alternatives I find is like 3x the price.

You gave me an , Airbnb but for office space, you can only go in the day, get at least a desk/chair/internet. Might exist already idk.

Not a bad idea. I know some people rent a single desk in some other companies office. Problem is you kinda need to know the owner to find those deals

…

A company called Spacious to do this with restaurant spaces that aren’t used during the day. Always seemed like a good idea to me, but they went under.

a szerveren lévő cookie adatokat és egyéb nyomkövető sz@rokat is a Google kezeli, én nem igazán szoktam ezekből látni semmit, se ip-t, se semmit, a Google inkább keresőmotor, mint mesterséges intelligencia alkalmazás, de ma már hibrid technológiával dolgozik minden MI és kereső

Google also manages the cookie data and other tracking s@rs on the server, I don't really see anything from these, no IP, nothing, Google is more of a search engine than an artificial intelligence application, but today all AI and search engines work with hybrid technology

Hello world

Run Claude code in docker sandbox (sbx) to ensure it only has current folder access and limited or no network access. Especially since a lot of runs are now in “auto mode”. Unless even this is not really so safe!?

Claude will run on auto mode only if you tell it to do it.

…

They've changed the default -

Ah, wow, TIL! Hmm, it is evident I need to visit their blog at least once a week now. Thanks!

wait a sec... something here is not right.. running AI in a docker sandbox... ~~

Bring back partial anterior encephalectomies

Which part of the brain would you remove?

It seems like removing some of the connections between the anterior and frontal cortices could have positive effects.

I think you're perfect as you are :)

…

^____^

I want to become an excellent marketing person😭😭

I hate it when I don’t remember if I took my midday pill or not. Not that it matters a lot, but still, annoying. I have notifications set up but I discard them by habit because they are exact times and my sleep pattern fluctuates.

I once saw someone flip their pill bottle upside down after taking a pill. Not sure it'd help me, because I suspect that somehow I'd still only pay half-attention when taking pills and so still get forgetful and confused :shrug:

It actually works!

Watched Black Bird ep 1. Definitely lived up to the great reviews.

看到其他文章有自動翻譯，我覺得很酷

I think it's really cool to see other articles with automatic translation.

所以我來嘗試一下自動翻譯的文章功能，但發現自動翻譯只有在瀏覽器上，行動裝置要自己手動按翻譯功能。

So I tried the automatic article translation feature, but found that automatic translation only works in the browser; on mobile devices, you have to manually press the translation button.

Thinking of Zik all the time. It’s the spark that ignited my imagination. I’ve always loved memories.

Power and money somehow emit the whackadoodle in all of us.

I actually disagree. This guy has been very good at performing The Good Guy for a very long time, but there have been signs all along.

Well said. My post was glib. More correctly, they are multipliers. Same goes for Musk. "Musk’s ex-wife Justine, whom he married in 2000 and divorced in 2008, says the man the world began to see in 2020 was the one she’d always known." -slate.com

Introduced an MCP server this morning for the app I'm working on (getonmain.com), based on a user request. Curious to see how/if folks use it.

Currently it provides a single read-only tool that lets agents fetch all the data in Main about the user's home (details about the home itself, systems/appliances, documents, any repairs they've logged). I think it could get interesting once we provide additional tools for logging repairs, upgrades, and more into the home's memory.