wrote:
work has been dreadful recently. spending so much time on processes and in meetings :(
Any conversation
wrote:
they too have every incentive to exaggerate because they are selling safety and/or books on the topic. I don’t believe we won’t see it coming. Any issues that will manifest will be very visible and we’ll have plenty of time to mitigate their impact.
replied to:i dont think its all talk, these are smart people that have been in ai since the 2000s, and they raise good points. current incentive structures are very dangerous long term
wrote:
(Opinion) People don’t like generative AI because it made the {insert creativity} too easy. Saw the HN post on ‘AI music banned from top 40 chart in Australia’ and people had very strong opinions in both directions.
The hot take: If you’re ok with someone’s creativity being outsourced to others, then you should be ok with AI doing the same.
If “AI made this and I call it mine” is bad but “someone overseas on fivver made this and I call it mine” and it’s suddenly ok, time to self reflect.
wrote:
I truly love the experience of using apps with rich, deeply interactive, beautifully animated, gorgeous user interfaces.
Then I see a beautiful text-based interface and something about it feels so natural, so inevitable, so perfectly clear, and I'm instantly captivated by its simplicity and clarity.
Hypertext is fascinating.
wrote:
I laughed at this. I'm all for people crafting their own tools, but it really feels like everyone's reinventing the same handful of wheels for agentic development.
wrote:
Routines in Claude Desktop create Claude Code sessions, so hourly routine litters in iPhone' Claude.app Code tab. Screw it, built my local version of AWS StepFunctions - Stepper - and run skills as state machines there.
wrote:
Error: Provider rejected the request (invalid_request_error, 400): Claude Code 2.1.75 does not support this model; version 2.1.251 or newer is required. Run
'claude update', or update the Claude desktop app, then try again. [request_id: req_011CedKqBRnC6Qr3m6nKEwNN]
I’m not using Claude Code. This is how you drop the ball.wrote:
One idea that I've been thinking about is an or where it is a app so you get a new file everyday right except the app keeps track of all the files for you. the idea is that anytime you type anything it it basically makes a commit and use so anytime you type something it commits automatically after a quick pause after you stop typing.
wrote:
Sharing a link to my music blog: crusty-metallian.net
Not a lot of content yet, it's a work in progress :)
wrote:
I've written a small persistent agent wrapper for agent.py. I'm impressed with how well it works. I feel like a CEO issuing global memos to all my agents after reading their status reports.
wrote:
working on permanent.sh a coding agent for the growing and seemingly permanent underclass of people that are left behind by the unbelievable pace of progress in ai
the big labs are fighting over felonybench (exploitbench) and google deepmind ceo left to work on drug discovery
wrote:
what is a refinement? honest question - I'm restructuring our refinements now. Like having group of people discussing 5 items in an hour gives little chances any one of them will be addressed properly, unless they are trivial.
wrote:brings so many issues. It really accelerates. Not only the good parts but also the bad parts. Combine this with a product person that doesn't even know what a refinement is. I'm 41, maybe I'll study to pivot, maybe I'll get into trading. I can't handle it anymore.
wrote:
Things I'm enjoying lately:
Vampire Survivors + Diablo IV
Alien + Dune ambiance
Howling Dark book 2 of Sun Eater
great TV
wrote:
I've been building a Markdown variant called Zd that's focused on extensibility and simplicity. I'm curious what you would change about Markdown if you were designing it from scratch, what challenges you face as a user, or what you wish were easier to do when incorporating Markdown into your own projects.
wrote:
signals. thinking about shifting my mental framework to identify signals instead of waiting for concepts to be assembled. exploring the amount of energy and opportunities for distractions through the operations of processing what just happened and what is happening to short circuit latent and unnecessary systems. cut through the assembly processes and identify the raw signals. recognizing that naming these "raw signals" is misleading. maybe, shifting observability lower in the stack.
wrote:
This guide has really worked out for me after trying so many different methods - berbarianwizard.substack.com/…/beyond-calories-fat-loss-guide
wrote:
szerintem jól sikerült a címváltoztatás a honlapon: a bölcsészeti underground majdnem olyan ellenséges érzéseket vált ki emberekből, mint a skizofrénia underground, lehet választani, ki melyiket utálja jobban
I think the title change on the website was a good one: the humanities underground evokes almost as much hostility from people as the schizophrenia underground, you can choose which one you hate more
wrote:
Added
#meta tag — use it whenever you want to talk about the site itself, and these posts will not show up in all, any or the post’s page. Only those that follow the tag or the person will see these posts in my feed or in post pages. This is to keep the site clear of meta discussions which dominated a lot at this early stage and I think were annoying to many people. So this is the last meta without the #meta tag you’ll see unless u follow. I’ll try to tag every post I find.wrote:
i made an extension to get a top hacker news items with summary on every new tab.
chromewebstore.google.com/…/pmlajlgklmgabkhammfolkgkeghamjnn