Hacker Newsnew | past | comments | ask | show | jobs | submit | scosman's commentslogin

also: inference time scaling. Generating more tokens when getting to an answer helps produce better answers.

Not all extra tokens help, but optimizing for minimal length when the model was RL'd on task performance seems detrimental.


I liked playing with the completion models (davinci 2/3). It was a challenge to arrange a scenario for it to complete in a way that gave me the information I wanted.

That was how I realized why the chat interfaces like to start with all that seemingly unnecessary/redundant text.

It basically seeds a document/dialogue for it to complete, so if you make it start out terse, then it will be less likely to get the right nuance for the rest of the inference.


Is there a way to view IG pages without logging in? I would love to delete the app and setup privacy redirect.


It depends. If there's a share id (?igsh=xxc) in the link usually no, but if you remove it usually yes. Opening more than a few posts/stories will result in a popup to sign in, but at least the core page and introduction should be visible.


Change the URL from instagram.com to imginn.com. There are browser extensions which will do it automatically.


Doesn't work..


Try switching to desktop mode


it still forces you to log in when you scroll and you can't view any post iirc. Maybe solvable with ublock filters or some console commands but I haven't bothered


You can view posts by opening them in a new tab.


> Where it breaks down is any task where you discover the requirements during implementation

Often you can find these during design. Design phases felt like a waste of time when you could just start coding and find the issues as you go. Now I find it faster to do a detailed design, then hand it over to agents to code. You can front-load the hard decisions and document the plan.

Sometimes the agent might discover a real technical constraint during dev, but that's rare if the plan is detailed. If so you can always update the plan, and just restart the agent from scratch.

This is my (cheesily named) process: https://github.com/scosman/vibe-crafting


I opened a startup's page the other day, and their streaming demo video was 550mb


What's the best "docker with openclaw" currently available? I have my own computers to run it on (I don't need a server). I want to play around, but containerized to avoid the security risk of MacOS app.

There seem to be about 20 options, and new ones every day. Any consensus on the best few are, and their tradeoffs?


I am still searching for a compose up -d to this day, but without success. And the other poster want me to create a k8s cluster for a bot?!?!


Try mine:

https://github.com/skorokithakis/stavrobot

It does indeed only need compose up -d.


Does it support local llm, on openai standard, and out of the box web browsing?


What's web browsing? Yes on the rest.


Web browsing as give the bot access to the web with an headless chrome install.


Oh, no, you'd need a plugin for that. Out of the box it has curl and web searches.


right? From what I can tell it really needs MacOS, so alts are really parallel implementations (nanoClaw, etc).


I'm working on KubeClaw: https://kubeclaw.ai - a bit more sophisticated then all the open source cloud native implementations I found in my research.


update: I did a standard openclaw install in docker and it works great.

Their docs are confusing. It read like the gateway is in docker, and you'll need a connected computer. However the gateway can run agents/web_search/etc. The tools you'd expect to work in a CLI environment. Even headless browsers.

Docs: https://docs.openclaw.ai/install/docker


I have sandbox-exec setup for Claude like you suggest, but I’m not sure every CLI supports it? Claude only added it a month or two ago. A wrapper CLI that allows any command to be sandboxed is pretty appealing (Claude config was not trivial).

The downside is that it requires access to more than it technically needs (Claude keys for example). I’m working on a version where you sandbox the agent’s Bash tool, not the agent itself. https://github.com/Kiln-AI/Kilntainers


I like the idea but not the MCP part.

How about using bash-tool to intercept the commands and then passing them onto the containers?

https://github.com/vercel-labs/bash-tool


That's exactly what it does -- the bash commands are passed into the containers. It also manages container lifecycle (starting on first request, cleanup on connection shutdown).

If you're using an agent tool that already includes an existing bash tool which calls host OS, just remove that one and add this.


My bad, looks like I misunderstood how bash-tool works.

Then how about running Claude Code or your harness of choice inside bubblewrap with a shim/stub for the base binary?

https://github.com/containers/bubblewrap


Apple APIs yes. But there’s also an overhead when running containers like docker on Mac (and windows). Only Linux has near-zero overhead.


Right, because on Mac (and windows) you’re running a VM rather than just setting up kernel namespaces. How cpu and network intensive are these pets? Or is it more of a principle thing, which I totally understand?

I prefer containerization because it gives me a repeatable environment that I know works, where on my system things can change as the os updates and applications evolve.

But I can understand the benefit of sandboxing for sure! Thank you.


very roughly: not that bad but not zero. I see docker taking a continuous 1/2% CPU on MacOS when running its host, where sandbox-exec or containers on linux are zero unless used.

If you prefer containers, use containers.


Read as PyPi and almost had heart attack


Bear is my fav answer to this. It's mostly "just markdown", but great design. Nice Apple cloud sync integration. Just the right touch of formatting ("# Header" renders bigger and hash is grey, but still markdown, tables are visually tables, images render inline, etc.


Similarly https://prose.sh which is a markdown blog you just rsync to their service


This isn't from the TanStack creators, despite using their name (see footer disclaimer).

They are pitching this as a launch (first 20 buyers get a discount!), but their YouTube review videos are 5 months old with 67k views (looks like paid creators).

This looks like just another paid template hustle.


what you mean? It is for TanStack developers. The footer includes a disclaimer that it's not part of the official tanstack brand/team.

And what 5months old video? I just launched it 2 days ago


from != for. You can't just use someone else's trademark in your product name, especially when related to it.

Re:youtube - you link to several videos in the section "Why TanStack Start". Looking closer, they are actually about a project "Tanstack Start" (which is actually by TanStack folks) and not about this project "Tanstack Starter Kit". You linking to them confused me (as it seems it was intended to). Linking to videos as testimonials, knowing they aren't about your product, but the similarly named pre-existing product is very sketchy.

- Your logo is near copy of theirs

- Your name is near copy of theirs (just adding "er Kit")

- You link to videos about them from your homepage in a "Why" section


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: