Harry Jones

Technical Program Manager in quantum computing | Building practical AI tools | Cloud, engineering delivery & complex systems | PMP · CEng

[Harry Jones @hwhjones]

tried extracting "efficiency" insights purely from metadata in a new burnrate branch and failed.

metadata is great for filtering and cost, but the real “why” only showed up in the actual log details.

lesson: design for both, but never assume metadata is enough.

[Tibo @thsottiaux]

To celebrate a week of efficiency and let you run 100'000 Luna threads this weekend... that's right... wait for it... I have reset usage limits for Codex and ChatGPT Work.

Enjoy.

[Pia Szabo @0xPia]

quarterly reminder to use this prompt to get your AI writing to sound better:

No antithesis. No corrective negation. No paragraph pinning. No parataxis. No summary beats. No rhetorical crutches. No negative parallelisms. No negative anaphoras. No contrasting pairs. No rule of three. No em dashes. No throat-clearing openers. No landing sentences. No setup/payoff constructions. No parallel sentence structures within a paragraph. Vary sentence length unpredictably. No stacked noun phrases. No filler intensifiers (genuinely, really, truly, actually). No corporate-register verbs (leverage, underscore, reflect). No nominalization. No hedging qualifiers. Write for the spoken voice. No performed enthusiasm.

[Tibo @thsottiaux]

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.

[Harry Jones @hwhjones]

@tdinh_me book is written like a "stream of consciousness" / intentionally hard to follow - I suggest reading it first without any information first up - the cyberspace is basically the matrix that's all you need haha

[Apple TV @AppleTV]

See you on the other side, cowboy.

#Neuromancer — January 22

[Harry Jones @hwhjones]

@thsottiaux 🥹 thanks! making it banked would be even better

[Harry Jones @hwhjones]

@lapodev same

[Harry Jones @hwhjones]

@TorukMakto1406 nice work, from the UI it appears to be more related to API usage & cost - are you able to link it to % usage of paid plans with codex etc or leave that to their specific dashboards?

[Harry Jones @hwhjones]

@rhnfzl nice, doing something similar. are you able to correlate the logs with % usage on various paid plans?

[Harry Jones @hwhjones]

if anyone uses Codex or ccusage and is happy to compare results on the same local logs, let me know.

i'm mainly interested in understanding where (and why) the totals differ.

[Harry Jones @hwhjones]

i'm pretty new to Codex and Claude, and I wanted a better way to understand where my usage was actually going. after watching the usage % disappear, BurnRate seemed like a fitting name:

v0.1.1: https://t.co/WsImwcYkXw