Fascinating read. I didn't know $1,200 for a lamp was a thing but clearly there's a market for it and you priced it better than Coolest Cooler or I would have.
Floppy is a race of robotic jackalopes, known for their floppy ears. A "Single Floppy" is a rare subset of that species where only one ear flops down due to a random mutation of their hardware.
> What I've come to realise is that the power of having a bash sandbox with a programming language and API access to systems, combined with an agentic harness, results in outrageously good results for non technical users.
I would argue if they're using all that tooling, they _are_ technical users.
> All other 25 GbE adapter solutions I’ve found so far ... have a spinning fan. ... the biggest downside of the PX adapter is that it gets really hot, like not touchable hot. Sometimes, either the network connection silently disappeared or (sadly) my Mac crashed with a kernel panic in the network driver. ... Other than that, the PX seems to do the job
This is exactly my experience. On paper and in laboratory settings with 64-core machines and 128GB memory, AV1/AVIF is better in every way but in the real world it's too taxing on ordinary hardware.
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 interested could easily replicate it in an afternoon with their favourite Agent CLI.
[*] In reality, I created this something like 6 years ago, before LLMs were popular, originally as a way to inspect all outgoing HTTP(s) traffic from all the apps installed in my macOS system. Then, a few months ago, when I started using Codex CLI, I made some modifications to inspect Agent CLI calls too.
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 can get the whole auth flow and initial conversation starters using Burp Suite and its certificate, but the Gemini chat responses fail in the CLI, which I understand is due to how Burp handles HTTP2 (you can see the valid responses inside Burp Suite).
Tried with gemini and gave more headaches than anything else, would love if you can help me adding it to sherlock... I use claude and gemini, claude mainly for coding, so wanted to set it up first. With gemini, ran into the same problem that you did...
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 :)
Kind of yes... But with a nice cli so that you don't have to set it up just run "sherlock claude" and "sherlock start" on two terminals and everything that claude sends in that session then it will be stored. So no proxy set up or anything, just simple terminal commands. :)
reply