38 karma · joined February 3, 2026
Imagine then, after many years during some awards: and the best support role goes to ... NMAP :D
I agree, this story above would be a perfect for another asianometry document.
I worry only how long it will be supported? I hope there will be small community maintaining it ;)
Once again nice project and good luck.
That's why many universities declare in their charter that research doesn't have to be practical. The practicality of RSA asymmetric encryption only became practical with the advent of the internet ;)
I got similar feeling. I'm new here, but got a feeling that some comments are like bot generated.
Such low p-values are proof that something is going on.
Hipotesis (after your recent word statistics): that some bots are "bumping up" AI related subjects. Maybe some companies using LLM tools want to promote some their products ;)
marginalia_nu respect for your work :)
PS. There left 21 bytes (21 * 0x00 - from 0x01e0 to 0x01fd). Maybe something can be packed there ;)
You mentioned "harness engineering". How do you approach building "actual programmed tools" (like screenshot scripts) specifically for an LLM's consumption rather than a human's? Are there specific output formats or constraints you’ve found most effective?
I'm old school. I used to do "manual bisection" on git history by just `git checkout <commit_id>` until I find first introducing bug commit.
Then another "bisection" on commit changes until minimal change found.
Deterministic bugs are quite "fine". For me personally worst are randomly occurring bugs in specific conditions for eg. some race conditions.
Got two questions: 1. How fast it can ride ? If I good estimate (based on max 2750 RPMs for electric motor MY1016 350W 36V, gear ratio ~100:1 and height of rear wheel ~0.5m) it should got about 0.8 m/sec. So really safe for kids and dad :)
2. How long does the battery last ?
It's becoming increasingly difficult these days, with so many things competing for your attention and "brain-deadening" you. It was a wonderful thing to be bored and play around with math. My favorite moments were the epiphany - that there is some hidden connection between math areas or something got new meaning.
When you are an experienced developer and you "struggle" writing manually some code this is important warning indicator about project architecture - that something is wrong in it.
For such cases I like to step back and think about redesign/refactor. When coding goes smoothly, some "unpredicted" customer changes can be added easly into project then it is the best indicator that architecture is fine.
That's my humble human opinion ;)