https://left4more.com/tags/llms/Recent content in Llms on Left 4 MoreHugoen-auThu, 14 May 2026 01:36:50 +1000https://left4more.com/posts/ai-benchmarks-are-lying-to-you-but-not-in-the-way/Thu, 14 May 2026 01:36:50 +1000https://left4more.com/posts/ai-benchmarks-are-lying-to-you-but-not-in-the-way/<p>There&rsquo;s a post doing the rounds this week about GPT-5.5 cracking something called ProgramBench for the first time. It&rsquo;s a software engineering benchmark that&rsquo;s been resistant to frontier models until now, and the result is genuinely interesting. But the discussion underneath it is, predictably, a mess.</p> <p>Some of it is the usual stuff: people declaring their preferred model the winner, others pointing out the charts are misleading, a few genuinely useful technical observations buried under the noise. Normal internet discourse. What caught my attention wasn&rsquo;t the headline result though. It was a quieter observation someone made about the benchmark itself.</p>