Live data from Hacker News

Reverse-engineering is cheap now

simonwillison.net

31–40 of 42 posts

Re: Reverse-engineering is cheap now

#31

what's the deal with empty half-a-page-of-text posts lately? is this like the ultimate form of "headline is all you need"? I came here wanting to see after-action-report of someone actually using Ai or wtvr for reverse-engineering. Instead I got "I heard it was so. The end"

Ha. It does read like that. And Mr Willison could be forgiven since it is his blog.

Maybe he had a particular audience in mind when he wrote it. An audience for whom the mere realization would rock the foundations of their stolid and boring lives.

On the other hand, I’ve watched the movie Paycheck (2003), so my imagination has a high bar before it’s rocked by mere suggestion. Therefore, I wonder why the OP user @edward thought it was worthy of our attention.

I expected to read their excited engagement with others here, but alas no. It’s a mystery.

Re: Reverse-engineering is cheap now

#32

Cheap is a relative term. How many people would pay $5 to reverse engineer a device in their home? There's no way to make a profit off reverse engineering home devices so I expect while this is likely to be one of the most groundbreaking impacts of LLMs, it won't see a ton of adoption until token costs come down.

Sounds like a businesses opportunity to do it at scale! Send $20 pi zero that will reflash expensive camera, that is out of support. Or do mail business, with reflashing devices. There are billions out of support devices, and rework is great industry in China. In US you sadly hit legal BS if doing it commercially...

I think its more a case of, when/if this kind of LLM can be run on a normal desktop then it'll become a big deal. But its also not the kind of work thats economically transformative at all

Re: Reverse-engineering is cheap now

#33
post #20
post #3

I was doing this the last few weekends with some LoRa smart home devices and a thermal shipping label printer. Also this weekend I found out that Claude is better at writing Home Assistant automations than I am and I have been doing it for years.

Do you give Claude access to HA somehow? Or how does it get the relevant device names/ids?

Yes, using the API - I gave it an API key in an environment variable.

Re: Reverse-engineering is cheap now

#34

what's the deal with empty half-a-page-of-text posts lately? is this like the ultimate form of "headline is all you need"? I came here wanting to see after-action-report of someone actually using Ai or wtvr for reverse-engineering. Instead I got "I heard it was so. The end"

I've used it to help me clean up and reverse malware samples to give the person running it problems. It's very good at taking the obfuscation apart and translating it into something easier to read. I can often get it to completely vibecode string decryption functions for me so I can get what exfils they're using and the like.

Doing the same by hand can be really time consuming and difficult depending on how many obfuscation measures are layered on top.

Re: Reverse-engineering is cheap now

#35

what's the deal with empty half-a-page-of-text posts lately? is this like the ultimate form of "headline is all you need"? I came here wanting to see after-action-report of someone actually using Ai or wtvr for reverse-engineering. Instead I got "I heard it was so. The end"

I disagree. It's a high signal article that can create great discussions on what people on HN have reverse-engineered with AI.

For example, just yesterday I reverse engineered the internal API of a SAAS tool we use and it allowed me to gain programmatic access to data that was only available in their slow clunky UI.

Re: Reverse-engineering is cheap now

#36

what's the deal with empty half-a-page-of-text posts lately? is this like the ultimate form of "headline is all you need"? I came here wanting to see after-action-report of someone actually using Ai or wtvr for reverse-engineering. Instead I got "I heard it was so. The end"

I suspect this article got upvoted partly for the headline & content, and partly because of who said it. Lots of people already have a good feel for the AI/journalism niche Simon Willison occupies, and can use that background knowledge to read into his words more productively.

Re: Reverse-engineering is cheap now

#37
post #35

what's the deal with empty half-a-page-of-text posts lately? is this like the ultimate form of "headline is all you need"? I came here wanting to see after-action-report of someone actually using Ai or wtvr for reverse-engineering. Instead I got "I heard it was so. The end"

I disagree. It's a high signal article that can create great discussions on what people on HN have reverse-engineered with AI. For example, just yesterday I reverse engineered the internal API of a SAAS tool we use and it allowed me to gain programmatic access to data that was only available in their slow clunky UI.

it's a high signal headline

the article itself is worthless, and nobody in the comments seem to even interact with its content, you included

Re: Reverse-engineering is cheap now

#38
post #4

what are some stuff that people are interested in reverse engineering ? ive never done it before but recently got interested after people started porting mario 64 to the playstation.

I started with Lineage 2 - RE the network protocol, building own implementation that could communicate to the server, than fighting with protected binaries (anti-VM, anti-debug). That was interesting.

Re: Reverse-engineering is cheap now

#39

Earlier quoted context omitted.

OBD vehicle diagnostic software.

thats a good one. even better if ya open source it ;)

FreeSSM is already open source. It's reversed Subaru SSM diagnostic protocol and wrapped a tool around it. That was ~15 years ago, long before any of the AI stuff.

Re: Reverse-engineering is cheap now

#40

Earlier quoted context omitted.

thats a good one. even better if ya open source it ;)

FreeSSM is already open source. It's reversed Subaru SSM diagnostic protocol and wrapped a tool around it. That was ~15 years ago, long before any of the AI stuff.

The point was rather that reverse engineering the CAN-bus protocol or existing software that already does it for your vehicle of interest is now by far easier through the usage of AI models than it was before - FWIW I could have done it before with the technical skills I have but ROI for me personally was too low. Now I am really considering it.
Post reply on HN