Let coding agent see what it builds as X11 GUI application. Get it involved into the dev->test->validation loop.

Currently only one skill based on xvfb, designing and adding more.

I'm also working on a cross-platform solution (sandbox-exec on macOS). What if Apple finally drops this after long deprecation?

Let’s make something so popular and useful that they can’t drop it.

You can even simply by pass Rosetta 2 to get the kernel response:

# cat /proc/cpuinfo processor : 0 vendor_id : VirtualApple cpu family : 6 model : 142 model name : VirtualApple @ 2.50GHz stepping : 10 cpu MHz : 2502.057 cache size : 6144 KB physical id : 0 siblings : 8 core id : 0 cpu cores : 8 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : no cpuid level : 22 wp : yes flags : fpu tsc de cx8 apic sep cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx lm rep_good nopl pni cpuid pclmulqdq ssse3 cx16 sse4_1 popcnt sse4_2 aes lahf_lm movbe fma avx f16c rdrand bmi1 avx2 bmi2 bugs : bogomips : 5184.11 clflush size : 64 cache_alignment : 64 address sizes : 39 bits physical, 48 bits virtual power management:

# cd /proc # cat cpuinfo processor : 0 BogoMIPS : 48.00 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 asimddp sha512 asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp flagm2 frint CPU implementer : 0x61 CPU architecture: 8 CPU variant : 0x0 CPU part : 0x000 CPU revision : 0

Yeah, I guess it's losing some contexts. Still need human work if want to make it really work on Linux...

WIP ;) The final target might be to get Intel's Houdini-like binary (but for Intel instructions)

Just clarified in the README (by AI as well): https://github.com/Inokinoki/attesor?tab=readme-ov-file#comp...

Sharing my thoughts on Open Source in this AI era - after my 10-year contribution experiences.

I would like to introduce the Street Stall mode - where projects from individual authors are more and more popular.

And the vibe coding just enforce the Cathedrale in the companies.

A quick review on ollama, how it leverages its hero behind - llama.cpp, how it detects and leverages the hardware.