GeekCoding101 make your way to geek
~ $ cat README.md

Hands-on notes on AI agents, LLMs and security.

I build it, run it, and read the logs before I write about it. Tutorials and teardowns on Claude and other models, OAuth and identity, Kubernetes, and the tools in between.

➜ ~ whoami
GeekCoding101 · AI, security & infra, tested by hand
➜ ~ ls -t posts | head -4
➜ ~ gh contributions --last-year
Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov
1983 contributions in the last year
Less More
➜ ~

Latest posts

All 78 posts
Terminal table of the benchmark: gpt-6.2-sol 22 of 22 correct in 140 s for $0.237, gpt-6.2-astra 22 of 22 in 207 s for $0.917, gpt-6.1-sol 22 of 22 in 253 s for $0.264, claude-opus-5-5 22 of 22 in 191 s for $0.856
New

GPT-6.2 Sol vs Astra vs 6.1 Sol: Tested, With Pricing

GPT-6.2 Sol vs Astra vs GPT-6.1 Sol (and Opus 5.5) on the same 9 graded API tasks: accuracy, speed, GPT-6.2 Sol pricing and the real cost per task.

8 min read
aillm