Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Interesting, if all software can be decompiled and copied what is the future of software. Will all software be SaaS? A time where the majority of PCs will be terminals? Game consoles are almost there. It's only a small jump for all software to go that way.
Edit: Here's a possibility.
The future of software is agent only software. We ask for a result, agent asks questions from us, agent uses the specialized software, user gets result. We subscribe to an AI assistant and specialized agents. We are almost there,at least the start. The future of PC's as we know them are numbered. OSs,CLI,compilers and whatever will melt into AI assistants. Say goodbye to writing software for people.
- I sense the approach overcomplicates things. I wonder how long this would have taken in a single session. Maybe this is actually a textbook example of something where subagents make sense, but when I first started LLMs I was often overcomplicating the workflow with all kinds of orchestration. Now I just use one agent, it better allows controlling the output even if the agent works slightly longer. Most time is spent by me writing prompts and reviewing work anyway (for me at least).by edg5000
- I think proprietary software will move into cloud. For example, a photo editor will keep processing algorithms on the server and client will be just caching the results and displaying them.
If you make a program with a simple logic, anyone can vibe-copy it in a day. You cannot sell it.
If you make a program with advanced algorithms and complicated math, anyone can clean-room reverse-engineer it (by 2 different AIs) and vibe-copy. Furthermore, reverse-engineered data, such as algorithms and secrets, will be embedded into weights of a next LLM version.
Yes cloud won't work when you have unstable Internet due to certain events, but having a program sometimes not working is better than having a program anyone can copy. Am I wrong?
Also, vibe-copy is a made up word.
by codedokode - It’s probably worth noting that the author is decompiling a game that he’s had ~10 years of experience modding. And has been involved in finding vulnerabilities in [0].
- The reason this cost so much is because the AI has the ridiculous goal of getting identical assembly output.
The agents would have had to mess around with compiler versions, optimisation options, and the phase of the moon as well.
If you just went for functional equivalence, it would probably cost 10x or 100x less tokens.
Another false economy was using Sonnet instead of a more intelligent model like Sol 6.1 (1), which would have cost more per token, but is 100x or so better at reverse engineering and coding and therefore can chew through the source code much quicker and make fewer mistakes, meaning less work needing to be scrapped.
In my testing doing a similar task, I ran multiple sonnet for weeks and burnt through ~$1000 in tokens to get 20% completion and output that was pretty bad. After switching to Sol 6.1, it finished the whole task in around 2 days, cost around $50, and it did it with zero supervision and a single /goal.
(1): struggle to use Opus for reverse engineering, too many safeguards. OAI has virtually none, and uses way less tokens so is more economical.
by aetherspawn - > The avid reader of my blog might have noticed that I had previously written two posts that have since been removed. Everyone else might now be wondering which game I am talking about. To both of you I can only say that corporate America was here to ruin our fun.
Call of Duty: Modern Warfare 2 (2009)
https://web.archive.org/web/20260925153118/https://momo5502....
https://web.archive.org/web/20260925153131/https://momo5502....
Come at me, corporate America.
by nvme0n1p1 - Unless you explicitly need byte-matching decompilation, there are significantly faster ways to produce a decompilation/C which is functionally equivalent. I need to post about this. What's been working for me is that for every function, Agent A is tasked with writing some code which is semantically equivalent to the original assembly, but not necessarily exactly the same. Agent A also writes tests. Agent A submits the implementation of the function and tests to the harness for it to judge. The harness runs both the original function and the submitted function in a virtual machine/simulator/emulator (the tests define function inputs and starting state). The harness will only accept the implementation if 1) the read/write sequence to RAM is identical to the original function's, and 2) there must be complete line and branch coverage of the original function being decompiled.
I've found this to be robust for decompiling games, while giving the agents enough freedom to write code that is readable and not waste a ton of time making sure e.g. instruction ordering, register assignments, etc. are all exactly the same. For me, having byte-matching decompilation is only one way to produce a decompilation I know is faithful to the original. This "high-level decompilation" process I just described is something agents can do much more quickly.
- 500B Luna-equivalent tokens, just for a little fun experiment, which they'll never be able to share widely for very obvious trademark reasons. Even if they could share, not sure exactly what the point would be.
Side projects can be cool and fun even if they have no points to them. Sometimes it's even better when there is no point.
But 500B Luna tokens, that's about 15 SF -> London round trips, or the average CO2 equivalent emissions of an american for about 15 months, based on napkin maths assuming average US energy mix to power the DCs.
Was it really worth it? Should we all start burping 18 tons of CO2 just because we came up with a fun little prompt idea? Should a side project really pollute as much as your neighbor's entire life for more than a year?
I know worrying about climate change is not trendy anymore but there as to be a limit to the amount of not-caring one can have, surely?
Congrats, i guess.