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.

I was skeptical on if this was just a Theo-scale problem, but the IO overhead on MacOS is kinda brutal. But remember: if you think the overhead is bad on Mac, it's twice as bad on NTFS

Its funny how everyone's idea of heaven is a complete untouched paradise, crystal clear waters, lush green forests, enough food for everyone, classless, moneyless, stateless, a Utopia of peace, unity andhappiness. But here on earth it's considered a leftist ideology.

Hey @theo 🙋🏻‍♂️ Have you looked into @tangled_org, seriously curious about your thoughts & what you'd change / don't like. Not yet promising I'll build it but I'm seriously exploring/considering. Earlier, I thought about a native jj backend + hub 🤔

"Zero downtime deployment" means your server never went offline. It says nothing about the users already on your site when you shipped. They're running old JS bundles, old React state, against a server that's already moved on. Next API call hits an endpoint that no longer exists. Checkout fails. Form resets. Zero downtime. Broken session. Version skew isn't a bug. It's structural. It happens on every deploy. The fix isn't preventing it; it's building systems that let multiple versions run together. Cookies, ingress routing, replica set management, and a control plane that handles the rest. Building this with @matteocollina on Wednesday. 8am PT / 5pm CEST → streamyard.com/watch/RnVyfVT…

in honor of 30k gh stars: "mise-en-place: the song" mise.jdx.dev/mise-en-place.h…

I’m gonna comment on this for a second time today. Shows like Little Bear, Blue’s Clues, etc need to make a comeback. They had deliberate pauses and incorporated space. We need to get our nervous systems in check again, and get our attention spans back. We need to cultivate more empty SPACE in our lives

Why do we not authenticate CLIs via Secure Enclave/TPM keys? It's impossible for them to be leaked. Is anyone doing this? I can't be the first to suggest it.