Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: A MitM proxy to see what your LLM tools are sending

github.com

Post reply on HN
Print view View original

21–30 of 128 posts

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#21

Post by pixl97 »

jmuncor wrote: post #18
3abiton wrote: post #17

Earlier quoted context omitted.

That's what LLMs enabled. Faster prototyping. Also lots of exposed servers and apps. It's never been more fun to be a cyber security researcher.

I think it just has been more fun being into computers overall!

It's interesting because if you're into computers it's more accessible than ever and there are more things you can mess with more cheaply than ever. I mean we have some real science fiction stuff going on. At the same time it's probably different for the newer generations. Computers were magical to me and a lot of that was because they were rare. Now they are everywhere, they are just a backdrop to everything else going on.

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#22

Post by jmuncor »

pixl97 wrote: post #21
jmuncor wrote: post #18

Earlier quoted context omitted.

I think it just has been more fun being into computers overall!

It's interesting because if you're into computers it's more accessible than ever and there are more things you can mess with more cheaply than ever. I mean we have some real science fiction stuff going on. At the same time it's probably different for the newer generations. Computers were magical to me and a lot of that was because they were rare. Now they are everywhere, they are just a backdrop to everything else go…

I agree, I remember when the feed forward NN were the shit! And now the LLMs are owning, I think this adoption pattern will start pulling a lot of innovations on other computer science fields. Networking, for example. But the ability to have that peer programer next to you makes it so much more fun to build, when before you had to spend a whole day debugging something, Claude now just helps you out and gives you time to build. Feels like long roadtrips with cruise control and lane keeping assist!

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#23

Post by jmuncor »

Havoc wrote: post #20

You don't need to mess with certificates - you can point CC at a HTTP endpoint and it'll happily play along. If you build a DIY proxy you can also mess with the prompt on the wire. Cut out portions of the system prompt etc. Or redirect it to a different endpoint based on specific conditions etc.

Have you tried this with Gemini? or Codex?

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#24

Post by paulirish »

tkp-415 wrote: post #9
guessmyname wrote: post #6

Earlier quoted context omitted.

> So is it just a wrapper around MitM Proxy? Yes. I created something similar months ago [*] but using Envoy Proxy [1], mkcert [2], my own Go (golang) server, and Little Snitch [3]. It works quite well. I was the first person to notice that Codex CLI now sends telemetry to ab.chatgpt.com and other curiosities like that, but I never bothered to open-source my implementation because I know that anyone genuinely interes…

Curious to see how you can get Gemini fully intercepted. I've been intercepting its HTTP requests by running it inside a docker container with: -e HTTP_PROXY= http://127.0.0.1:8080 -e HTTPS_PROXY= http://host.docker.internal:8080 -e NO_PROXY=localhost,127.0.0.1 It was working with mitmproxy for a very brief period, then the TLS handshake started failing and it kept requesting for re-authentication when proxied. You c…

Gemini CLI is open source. Don't need to intercept at the network when you can just add inspectGeminiApiRequest() in the source. (I suggest it because I've been maintaining a personal branch with exactly that :)

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#26

Post by jmuncor »

elphard wrote: post #25

This is fantastic. Claude doesn't make it easy to inspect what it's sending - which would actually be really useful for refining the project-specific prompts.

Love you like it!! Let me know any ideas to improve it... I was thining in the direction of a file system and protocol for the md files, or dynamic context building. But would love to hear what you think.

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#27

Post by cedws »

EMM_386 wrote: post #4

This is great. When I work with AI on large, tricky code bases I try to do a collaboration where it hands off things to me that may result in large number of tokens (excess tool calls, unprecise searches, verbose output, reading large files without a range specified, etc.). This will help narrow down exactly which to still handle manually to best keep within token budgets. Note: "yourusername" in install git clone in…

I've been trying to get token usage down by instructing Claude to stop being so verbose (saying what it's going to do beforehand, saying what it just did, spitting out pointless file trees) but it ignores my instructions. It could be that the model is just hard to steer away from doing that... or Anthropic want it to waste tokens so you burn through your usage quickly.

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#29

Post by thehamkercat »

jmuncor wrote: post #23
Havoc wrote: post #20

You don't need to mess with certificates - you can point CC at a HTTP endpoint and it'll happily play along. If you build a DIY proxy you can also mess with the prompt on the wire. Cut out portions of the system prompt etc. Or redirect it to a different endpoint based on specific conditions etc.

Have you tried this with Gemini? or Codex?

Have tried with gemini-cli and claude-code both, it works, honestly, it should work with most if not all cli clients

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#30

Post by actionfromafar »

jmuncor wrote: post #28
andrewstuart wrote: post #19

What about SSL/certificates ?

I didn't understand the quesion I am sorry.

I also assumed Claude Code would need some kind of cert nudging to accept a proxy.

But it's in the README:

Prompt you to install it in your system trust store

Post reply on HN