May 1 · 11 min read · Yesterday around midnight, Anthropic dropped Opus 4.7. I had already lain down ready to sleep, but once the news broke I didn't end up sleeping; I got up and installed it to try it out. Hands-on Impressions of 4.7 There were no miracle moments of "so...
Join discussionMay 1 · 9 min read · The long-awaited OpenAI "potato" dropped today. Turns out it's not GPT-6, but GPT-5.5. I tried it out right after it came out and found that it fixed the thing that annoyed me most about 5.4: it finally started talking like a human. Back in the 5.4 d...
Join discussionApr 20 · 5 min read · Ollama Explained: The Fastest Way to Run Local AI Models in 2026 Everyone's obsessed with cloud AI while the smartest builders are running models locally — for free — and keeping total control of their data. If you've been paying any attention to the...
Join discussionApr 17 · 3 min read · Yesterday around midnight, Anthropic dropped Opus 4.7. I had already lain down to sleep, but the news kept me up. I got up and tried it out. First Impressions of 4.7 There was no "miracle moment" where something I previously couldn't solve suddenly w...
Join discussionApr 17 · 1 min read · Around midnight yesterday, Anthropic dropped Opus 4.7. I had already lain down to sleep, but the news kept me up, so I got up and installed it to try it out. How 4.7 Feels There was no miracle moment of "something I Originally published at https://...
Join discussionApr 14 · 7 min read · A few days ago, while researching text-to-video models, I noticed something that diverged significantly from my prior understanding: in the directions of text-to-image and text-to-video, Chinese companies' presence in the open-source community is far...
Join discussionApr 14 · 7 min read · A few days ago, while researching text-to-video models, I realized something that diverged significantly from my prior understanding: in text-to-image and text-to-video, Chinese companies' presence in the open-source community is far weaker than in l...
Join discussionApr 7 · 7 min read · A few days ago, while researching text-to-video models, I discovered something that differed significantly from my original understanding: in the directions of text-to-image and text-to-video, Chinese companies' presence in the open source community ...
Join discussionApr 5 · 5 min read · Modeling Decentralized Commerce Business Logic with Smart Contracts Introduction Lately, I've been diving deep into the architectural challenges of building truly decentralized commerce platforms. The traditional e-commerce model, while effective, is...
Join discussion
