Still a great story, great page and impressive reverse engineering. Isn't OpenClaw vs. he did it "himself" a bit analogue to the critique "oh, he wrote the firmware in C++ and let the compiler figure out the assembly code".
Maybe you wanted to see the assembly code, and that's fine. But he took a potentially difficult problem, found tools to solve it and documented (to some degree) the process?
Nice! I loved that phone, was one of my favourites. One of the only, if not the only phone I ever owned that had a metal shell that I an recall.
I had most of the N range, and was particularly interested in music ones, N95 was love/hate because the music button/reverse slide was so slow sometimes, and generally it just wasn't as good as N91 for music listening with its proper headphone jack placement, and always accessible controls.
What kind of magic did that HDD have that it could be thrown around like a phone typically is without the issues we would see if we'd handled a laptop with HDD the same way?
Had an accelerometer that turned off hard drive when motion detected. High end ibm thinkpads had that too. Turns out if seek head is parked properly, its fairly robust
N91 also had a ridiculously high quality DAC that beat pants off iPods of that gen.
I am not necessarily against AI, but in this case, I also lost interest at that point. I love reading about reverse engineering, and to me the first part of the article felt like it was leading up to that. But then it ended with what to me feels like "and then I asked AI to finish the project for me, which it did". That's not a criticism by the way, there's nothing wrong with the author using AI to reach a certain goal. I just don't find that interesting personally.
I may not have felt this way if the article had discussed this step in as much detail as the first steps - describing what was done by the agent rather than just that an agent was used and the results. It all felt a bit “then it drew the rest of the goddamn owl”.
I’m not sure though - part of the appeal of this kind of article for me is the description of the human emotions - the highs and lows of doing the task - and that would possibly still have felt missing.
Edit: Actually, now that I say that, there was a lot missing. How was the circuit designed, for example? How were components selected?
I did finish the article, but for me, it was missing a discussion and review, probably manual improvement, of the code that came out of the LLM. Reverse-engineering means understanding a system that you didn't previously understand, which is still (with some degradation) possible while using an LLM.
Surprised me too. In the end, I guess it's a time-saving tool for a tedious task. But reduces the old-school grittiness of the adventure. Still an enjoyable read.
Almost every commenter in this thread explained this better than I could.
It's a bit like watching a 2 hour movie about a knight who'd been preparing to save his beloved princess from a dragon for 1h 59s, and then the screen fades to black, the narrator proclaims that the dragon is done, the knight marries the princess and they live happily ever after. Closing credits!
That’s a good question, and I can’t speak for the parent, but for me, I like reading about a person’s journey of discovery. There were many insights this person did not have because he turned the task over to a power tool. People can use whatever tools they want. I also can spend my attention however I like. Reading about someone using AI is just boring to me.
I found the old drive that worked with my Canon camera. It's a Hitachi 2GB Microdrive from 2003. It says CF+ Type-II. So larger, with a CompactFlash interface, boring in comparison.
One of my most delightful discoveries of the early 2000s was that iPod Minis used Microdrives that were pin-compatible with CompactFlash cards. I had a little cottage industry in the back of my office upgrading my coworkers’ old iPods to use bigger, solid state disks. I still have my 256GB iPod Mini. Aside from battery life, it still runs fine, and it is by far my favorite music player form factor.
I wonder what material they used for the platter. I once took apart a 1.8" drive, and got a big surprise when the platter suddenly shattered. I was expecting aluminum, not glass/ceramic substrate.
Maybe you wanted to see the assembly code, and that's fine. But he took a potentially difficult problem, found tools to solve it and documented (to some degree) the process?
Man do I miss the N-series, I had so many good phones in that era.
I had most of the N range, and was particularly interested in music ones, N95 was love/hate because the music button/reverse slide was so slow sometimes, and generally it just wasn't as good as N91 for music listening with its proper headphone jack placement, and always accessible controls.
What kind of magic did that HDD have that it could be thrown around like a phone typically is without the issues we would see if we'd handled a laptop with HDD the same way?
N91 also had a ridiculously high quality DAC that beat pants off iPods of that gen.
I may not have felt this way if the article had discussed this step in as much detail as the first steps - describing what was done by the agent rather than just that an agent was used and the results. It all felt a bit “then it drew the rest of the goddamn owl”.
I’m not sure though - part of the appeal of this kind of article for me is the description of the human emotions - the highs and lows of doing the task - and that would possibly still have felt missing.
Edit: Actually, now that I say that, there was a lot missing. How was the circuit designed, for example? How were components selected?
At least there's acknowledgement of limitations and it's not just hype. Overall a useful data point in terms of what's possible.
It's a bit like watching a 2 hour movie about a knight who'd been preparing to save his beloved princess from a dragon for 1h 59s, and then the screen fades to black, the narrator proclaims that the dragon is done, the knight marries the princess and they live happily ever after. Closing credits!
It is not an authentic display of pure skill
was this necessary? could've said "Code written by LLM" or something
I found the old drive that worked with my Canon camera. It's a Hitachi 2GB Microdrive from 2003. It says CF+ Type-II. So larger, with a CompactFlash interface, boring in comparison.
More history: https://en.wikipedia.org/wiki/Microdrive
I'm trying to remember the camera... Canon Powershot S1 IS maybe? It used a lot more battery running the microdrive.
I wonder what material they used for the platter. I once took apart a 1.8" drive, and got a big surprise when the platter suddenly shattered. I was expecting aluminum, not glass/ceramic substrate.
It is easier to ensure that glass substrates are perfectly plane and without any surface defects than for substrates made of aluminum alloy.
In 3.5" disks the risk of shattering becomes too great, so aluminum alloy is preferred.