大龙・無

Raw data from my ad hoc, semi scientific experiment, testing accuracy of pens. Who says I’m not a professional researcher.

Hello people of Sol! I've reset usage limits for all ChatGPT Work and Codex users. Together with that, a quick update on GPT-5.6 Sol usage limits. Over the past few weeks, many of you have told us that Sol was using your Codex limits faster than expected. To be clear, we have not reduced usage on any subscription plans. We’ve been digging into what was happening and have landed several improvements. As a result, we expect your usage to last around 18% longer during typical use of Sol. Some of you should already see significantly larger improvements from today. Tomorrow, we’ll also restore the five-hour limit that we temporarily paused while investigating. Here’s what we found: - GPT-5.6 Sol is much more willing to work for longer, make additional tool calls, and coordinate complex workflows across tools and subagents. That makes it better at solving hard problems, but some tasks were using far more than we intended. - Sol also works harder at the same reasoning effort than previous models. High on Sol can use more tokens than High did on GPT-5.5. - Programmatic tool calling, also referred to as code mode, gives Sol much more flexibility to run tool calls in parallel or continue working while waiting. But it also led to more responses per turn, more cached input tokens, and higher usage than expected. - This was particularly noticeable when Sol was waiting for tool calls to finish or running many web searches. We’ve improved how we handle both cases and are continuing to make code mode more efficient. - The impact was also very uneven. The median user actually found Sol quite token efficient, while some power users working on harder tasks saw their usage drain much faster. We were very focused on average and median usage before launch and missed some cases where the long tail could use significantly more usage. Sol is a significant step forward in what Codex can do, but capability and efficiency do not always improve at the same pace, and some issues only become clear once people are using the model at real-world scale. We should have recognized this sooner and been more upfront about it. You keep pushing the frontier and we’ll keep improving efficiency and sharing updates as we go.

Email interview with Vanguard Laboratory being posted soon He gets very in-depth with peptide testing questions With a few exceptions most of what passes for testing info around here is just a oneshot Claude question or at best referencing “that one clip I saw with Peter Magic” Stay tuned

running Kimi K3 locally is easy. you just need: - 1.5 TB of GPU memory - roughly 8 H100s - a small power substation

Does anyone have good experience to share on Methylene blue? I’m finally on the off ramp of Tesofensine (I don’t believe these should be used together) and have dug a lot into it, but it seems to be all over the place on user experiences. One of the things worth it? Nah? It’s cheap nonetheless.