Define easy. I am running 40+ probes to crack the best compression algorithm, and I spent $3. If you surgically tackle the problems, you can do really complicated work for less money than by assuming a frontier top model will one-shot everything.
Well, at least I spent lots of dollars, and I had to use those models the same way I am using local and cheap models, with the same results.
Right now I'm using several different models for reverse engineering (DS V4.1 Flash, MiMo V2.6 Flash, GLM-5.3 Flash, etc.), and so far none of them are able to finish the task - it's been ~1.5h and several dozen million tokens used, but still struggling with the algorithm (FFT and some other stuff on an image manipulation library, which appears to be hard for them).
On the other hand, Grok and GPT finish these tasks in <5min with no issues, and significantly better output.
It seems that these things goes on depending on each type of project. I've been reading reports and Grok 4.7 sucks at 3D, for example, really bad.
meerita · · focus · HN ↗
parineum · · focus · HN ↗
meerita · · focus · HN ↗
includenotfound · · focus · HN ↗
meerita · · focus · HN ↗
Well, at least I spent lots of dollars, and I had to use those models the same way I am using local and cheap models, with the same results.
includenotfound · · focus · HN ↗
On the other hand, Grok and GPT finish these tasks in <5min with no issues, and significantly better output.
meerita · · focus · HN ↗
includenotfound · · focus · HN ↗