Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
What is the most overrated college? what 83 AI models think
We asked 83 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 72% picked Harvard. See every answer, who searched the web, and who dissented.
12 min · 2,764 words
Introducing Humanity's Sixth Sense (HSS)
Elorian introduces Humanity's Sixth Sense, a benchmark built with Scale AI that measures the implicit, intuitive visual reasoning people do without thinking. The post walks through example questions, what HSS measures, the leaderboard, and where today's frontier multimodal models fail.
9 min · 2,080 words
The OLED Burn-In Test: 30-Month Update
We've spent the last two and a half years burning in our 4K QD-OLED monitor, and it's time to take another look at how it's holding up. It's been six months since the last update, and in that time we've continued to burn in our MSI MPG 321URX monitor on purpose by using it exclusively for productivity work.
12 min · 2,823 words
Which AI would you trust with your life? what 84 AI models think
We asked 84 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 15% picked Claude 3.5 Sonnet. See every answer and who dissented.
10 min · 2,252 words
Epoch AI presents early results from InnovationEval, which tests whether frontier models can independently rediscover a recent ML innovation, on-policy self-distillation. Despite budgets of 3,000 GPU-hours, neither Claude Fable 5 nor GPT-5.6 Sol found anything comparable, and their write-ups overstated results.
14 min · 3,282 words
WSL2 vs WSL3 Benchmarks: Performance, Memory, and Syscall Scaling
Tony Metzidis benchmarks WSL 2.6.3.0 (Linux 6.6) against WSL 3.0.2.0 (Linux 6.18) across kernel microbenchmarks, memory bandwidth and an end-to-end GoReleaser build, finding WSL3 roughly 5-60% faster depending on workload and explaining where the gains come from.
3 min · 757 words
Why Isn't The Industry Freaking Out About DeepSeek 4.1 Flash?
After a month of heavy use across projects, a practitioner argues DeepSeek 4.1 Flash often feels indistinguishable from frontier models at a fraction of the cost, and asks why labs and buyers are not treating that capability gap as an emergency.
3 min · 691 words
Does pineapple belong on pizza? what 83 AI models think
We asked 83 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 88% picked Yes. See every answer, who searched the web, and who dissented.
10 min · 2,348 words
Will there be a human-level AI before 2030? 83 AI models predict the result
We asked 83 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 67% picked No. See every answer, who searched the web, and who dissented.
14 min · 3,108 words
Pyramid-JiT: Low-Res Drafts, High-Res Images
Linum introduces Pyramid-JiT, a decoder-only pixel-space text-to-image architecture with no VAE that predicts the target image at several resolutions along the DiT trunk, reaching Linum v2's FD-DINOv2 on 11.3x fewer training samples and training in 4.3x fewer GPU-hours at 4x the pixels.
21 min · 4,822 words
Jev-Driven SRE Diagnosis: What Worked and What Failed
The SREGym team builds a Kubernetes incident-diagnosis pipeline with no LLM agent: a programmatic collector gathers cluster evidence and TypeSafe AI's Jev decision model picks root-cause candidates and supporting evidence. It passed 80 of 105 diagnoses (76.2%) across 21 SREGym-Lite faults with a 14.6s median, close to an LLM agent's score at far lower cost, and the post dissects the faults it failed.
7 min · 1,572 words
What is the biggest lie professors tell? what 83 AI models think
We asked 83 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 23% picked Exam Bait. See every answer, who searched the web, and who dissented.
11 min · 2,493 words
Which company will be the biggest in the world in 2030? 84 AI models predict the result
We asked 84 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 62% picked NVIDIA. See every answer, who searched the web, and who dissented.
13 min · 3,025 words
India vs West Indies, 1st T20I: 82 AI models predict the result
We asked 82 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 96% picked India. See every answer, who searched the web, and who dissented.
11 min · 2,451 words
Alex Kladov (matklad) explains his rule of thumb for micro benchmarks: tune the input size until a run takes about 300ms, so results read as easy integer milliseconds, fixed costs don't skew them, the numbers stay in a human-perceptible range, and repeated runs to eyeball variance stay fast.
1 min · 214 words
Would you let a student cheat if nobody would ever find out? what 85 AI models think
We asked 85 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 99% picked No. See every answer, who searched the web, and who dissented.
9 min · 2,171 words
Will TikTok still exist in 2030? 85 AI models predict the result
We asked 85 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 95% picked Yes. See every answer, who searched the web, and who dissented.
12 min · 2,652 words
Drake or Kendrick? what 84 AI models think
We asked 84 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 96% picked Kendrick Lamar. See every answer and who dissented.
11 min · 2,423 words
Will there be broad student loan forgiveness this presidential term? 82 AI models predict the result
We asked 82 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 99% picked No. See every answer, who searched the web, and who dissented.
10 min · 2,386 words
The Agent Said It Was Done. The Database Disagreed.
Microsoft’s ThinkingBox grades AI agents on backend records they leave behind—not chat claims—running isolated MCP tool sessions and scoring terminal state consistency across repeated trials; now available on Hugging Face.
13 min · 3,044 words