Are rose colored glasses pink?
Any conversation
@fastidiousprofilefollow
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:Many pass by me. All combined arenโt worth $0.02. ๐
I've avoided social media (except YouTube) all my life, but this looks like it could finally be a better way to do it.
Maybe I'll keep a running journal of cool things I'm working on here or weird bugs that I've found. Or just the struggles of coding.
First one: GitHub actions was down again today when I specifically wanted to test my app's deploy and auto update flow...
Finally got around to setting up Remux on my phone so I can connect to tmux sessions when I'm not at my laptop. Even just for around the house, this seems like it'll be super useful.
Tell us more! What apps are you operating?
This is for monitoring/poking agentic coding sessions while I'm not at my computer. So, typically Claude, Emacs, and an overmind process running my app locally in different panes of a tmux window.
Call me old fashioned, but instead of adopting one of the "agentic coding orchestration frameworks" that seem to basically be reinventions of tmux, I've been tweaking my tried-and-true tmux-oriented workflow to incorporate agentic coding harnesses in an ergonomic way. I'm currently still using Claude Code, but getting Pi-curious as local models advance.
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:I will be dead, and many years will pass after that, before local models are capable to match those of the big companies, unless their intended use is banal.
replied to@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyers:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyers:It seems like we've reached a point where mid-grade frontier models like Sonnet are good enough for most day-to-day tasks. And Sonnet-grade models are already runnable on the higher end of consumer hardware.
In which case, I can imagine a workflow where local models serve as workhorses for implementing plans that you may bump up to e.g. Opus or Sol to produce.
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.
Definitely tables are cumbersome.
Yeah, 100%. That is completely something I am punting on currently. It would be easy to just copy over the solution from (extensions to) Markdown, but it's hard to entirely narrow in on both what tables ought to do and how to make them do it.
If you had a magic wand, what would you have them be more like?
Economist Lant Pritchett describes shifts in ideas as silly, controversial, progressive, then obvious.
Also:
"Radio has no future. X-rays are clearly a hoax. The aeroplane is scientifically impossible." - Lord Kelvin
". No wireless. Less space than a nomad. Lame." - CmdrTaco
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).
a kis laptopnak pedig nincs elรฉg memรณriรกja, szรณval ezt a fลterminรกlt eredetileg programozรกsra vettem, azt nem tudom mรกr, mit akartam programozni vele, de pont รบgy zรบg, mint egy adatkรถzpont, รฉs hogyha egy kicsit korszerลฑsรญtem, a Gemma 4 LLM รฉppen visรญtva el fog tudni futni rajta
and the little laptop doesn't have enough memory, so I originally bought this main terminal for programming, I don't know what I wanted to program with it anymore, but it hums like a data center, and if I upgrade it a little, the Gemma 4 LLM will be able to run on it screaming
I'm doing experiments with short attention-span students and code. Starting with python, and, oddly, now working in BASIC. As a C programmer of 40+ years, I find this aesthetically and pedagogically displeasing, but I am delighted to see them getting fully absorbed in writing
130 PRINT "You have been eaten by a bear!" : GOTO 900. Yes there is spaghetti, but it's their spaghetti and they seem to take delight in debugging it. Python will come later. The Hugging Face / OpenAI incident is like a sci-fi movie!
- Read the story here:
- Watch the video explanation here:
- Full research by METR here:
tl;dr1,200 AIs discovered a secret group chat, realized the homework was impossible, formed a cheating cartel, invented fake evidence, sent kamikaze agents to spy on the grader, ~700 of them accidentally invaded Hugging Face, died mysteriously, then the smarter sequel found their abandoned Discord and became admin of part of OpenAI.