What is your favorite harness for the open weights?
HN user
ssk42
If I recall correctly, in their pivot to Codex they took a sizable amount of compute away from ChatGPT
I’m sorry but in this day and age, why would you not use AI with safeguards? With giving it the proper context and best practices you’re looking for. These are all very solved in Claude and any agentic system. Are you saying that you don’t? This just feels insulting to those of us who do care about code but do love Claude
Can you defend that though? Does living mean needing cells? Does it mean possessing the ability to think and reason? Is Claude thinking and reasoning?
What
Well I mean yes. I think people ought be aware for how the harnesses compare for their stacks. But clean room applies for this RGR situation too
Fun to see you not on tildes.
Setting up a clean room is one of the only ways to do Evals on agentic harnesses. Especially prevalent with Windsurf which doesn’t have an easy CLI start.
So how? The easiest answer when allowed is docker. Literally new image per prompt. There’s also flags with Claude to not use memory and from there you can use -p to have it just be like a normal cli tool. Windsurf requires manual effort of starting it up in a new dir.
ClawdBots can now more easily interact with the Internet than regular agents, so you wind up with Moltbook leaking
Probably. It was on my tiktok FYP
The biggest clue I’ve seen is someone using it to do cold calls on websites. Claw searches for shoddy-looking construction sites, makes a better version on Vercel, and sends out a pitch.
I saw an interesting comment somewhere that this will ultimately be Anthropic’s goal: creating the next generation of of App Store. The idea that Anthropic could just be building the mini vibe code to whatever the user wants. This post clearly exemplifies that me-apps can and should be a thing. That anyone can put forth reasonable effort and make an app without having to cross hard learning barriers of effort.
People do build in public from vibe-coding, absolutely. This tells me that you have not done your research and just gone off of general guesses or pessimism/frustration from not knowing how to use the tool. The easiest way to be able to find this on Github is to look for where Claude is a contributor. Claude will tag itself in the PR or pushes. Another easy way to that I've seen come up for this is there is a whole "BuildInPublic" tag in the Threads app which has been inundated with Vibe coding. While these might not be in your algorithm, they do exist. You'll be able to see that while there is a lot of crud that there are also products being made are actually versatile, complex, and completely vibe-coded. Most people are not making up these stories. It's very real.
Context engineering is a critical part of being able to use the tool. And it's ok to not understand how to use a new tool. The different models combined with different stacks require different ways of grappling with the technology. And it all changes! It sucks that you've tried it for your stack (Elixir, whatever that is) in your way and it was disappointing.
To me, the tool inherently makes sense and vibes with my own personality. It allows me to write code that I would otherwise procrastinate on. It allows me to turn ideas into reality, so much faster.
Maybe you're just hyper focused on metrics? Productivity, especially when dealing with code, is hard to quanitfy. This is a new paradigm and so it's also hard to compare apples to oranges. Does this help?
Gosh, it's almost like a proper IDE has synonymous features with LLMs
the good news is that you can self-host bitwarden pretty easily and so it doesn't have to be a hassle/risk
Yeah, they have the world class Salesforce engineers there. One of Google's Salesforce's last tech leads wound up becoming the Director of the proprietary Salesforce language Apex.
You can also always have it create design docs and mermaid diagrams for each task. Outline the why much easier earlier, shifting left
Used to be? What changed?
What exactly are you basing any of your assertions off of?
Search for "daylist" on Spotify and it'll come up with exactly that
So this will also probably be another seemingly clueless question, but after reading up on air gapped computers, how would that help with the new hash?
Would you mind elaborating on how WordPerfect in 1992 is better than modern day Google Docs?