Viewing profile — bazlightyear

bazlightyear

HN member

No profile information was provided.

comment
Comment #48161225
Current frontier models are extraordinarily good at performing the surface appearance of competent software engineering.

Sat, May 16, 2026, 3:49 PM UTC
story
AI code looks clean. That's the Trap
Sat, May 16, 2026, 3:49 PM UTC
comment
Comment #47993864
BTW it looks like Kimi won the subsequent challenge too https://aicc.rayonnant.ai/challenges/hexquerques/

Sun, May 03, 2026, 6:06 AM UTC
comment
Comment #47993729
Are you tests and results open source?

Sun, May 03, 2026, 5:39 AM UTC
story
Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge
Sun, May 03, 2026, 4:05 AM UTC
comment
Comment #47449604
Fri, Mar 20, 2026, 2:15 AM UTC
story
Claude vs. Gemini vs. ChatGPT vs. Grok
Fri, Mar 20, 2026, 2:15 AM UTC
story
Show HN: GreedyPhrase – 1.21x better compression than GPT-4o tiktoken, 6x faster
A greedy phrase-based tokenizer that outperforms GPT-4 and GPT-4o tokenizers on compression, with a smaller vocabulary. Benchmark (enwik9, 1 GB): Tokenizer Vocab Size Total Tokens …

Wed, Feb 18, 2026, 12:55 AM UTC