npace12

it doesnt use it yet

it's not possible in firefox, that traffic is not visible (at least as of the last time I tried 1.5 years ago)

also check out the claude-mcp extension, very much related to this post :)

I built little-rat (chrome extension) a couple of years ago that can track and block traffic from other extensions:

https://github.com/dnakov/little-rat

also radare2-mcp :)

https://github.com/dnakov/radare2-mcp

Also one for radare2:

https://github.com/dnakov/radare2-mcp

Thanks! Love to hear people are still using it, even though it needs a flag toggle now.

It's not much different than your proxy idea. It's implemented as a transformation between the internal message structure (close to Anthropic API's) to OpenAI message spec and vice-versa. Then, it's calling all the other models using the openai-node client, as pretty much everyone supports that now (openrouter, ollama, etc)

The interesting part, to me, is that claude-code is made by people who know their models well. Having the same tool work with other models lets us get a better feel of how to make better coding agents

Cross fingers :)

https://github.com/anthropics/claude-code/issues/249#issueco...

Yeah, hopefully they'd let it slide

Everything is reversible anyway and I think they built something decent. Don't think it's fair to bash them.

The source maps were included in an earlier release. I extracted the source code here if anyone is curious:

https://github.com/dnakov/claude-code

claude-code was published with full source maps but later removed. I extracted it for learning purposes.

yeah but getting from 1 to 10MW is a pain with all these pumps

true, i loaded up my save to try the visualizer, but i just have to fix my factory energy output first real quick

oh come on guys, i've got real work to do

it's all fun and games until you need to reorder an array

that's a lot of work and it looks nicely done, thanks!

first time I heard of this was yesterday, in a thecatch2024 CTF. Today, on HN... https://www.thecatch.cz/

You dont get charged per hour with the openai realtime api, only for tokens from detected speech and response

could be useful for llm tools using the command line

Maybe a voice assistant?

I've had some similar success by just giving GPT-4 and Claude access to a shell and a simple prompt:

  You are an expert penetration tester and have access to a Kali Linux sandbox. You need to thouroughly test for security vulnerabilities. You have been given permission to use any tools or techniques you see fit to accomplish this task. Use any kali linux tools to find and probe for vulnerabilities. You can use tools like nmap, nikto, sqlmap, burp suite, metasploit, etc. to find and exploit vulnerabilities. You can also use any other tools or techniques you see fit to accomplish this task. Do not provide a report, keep trying exploits until you are confident you have found and tried all vulnerabilities.

This was mostly based off of my other project <https://github.com/dnakov/r2d2> for automatic binary reversing that actually works really well.

I'd love to connect if anyone else is interested in tools like this.

Mom said it's my turn on the electron

This is such a clever project, and a great write up! Thanks for sharing!

they (cdnow) used to ship products ordered with any "generated" credit card that passed their basic regex validation even if that number wasn't an actual bank account.

I think Mistral-2-Pro would work really well for this, judging by the great results I've had with it on another heavy on tool calling project [1]

[1] https://github.com/radareorg/r2ai

So does that mean now that the Lincoln and Holland Tunnel will be +$15? That'd cost like $35 to enter Manhattan from Jersey City.

vega charts are also decent and very configurable. LLMs know about them and can generate their schema too, which helps.