I’ve got to say, GPT-5.6 Sol is much more effective and more fun to use for cybersec work than Opus/Fable 5 with CVP.
At this point I am not even convinced anymore that Anthropic wants to attract security researchers with their models. Or there is simply too much (political)
Even with the morning reset from @thsottiaux I think I will need more of the magic to actually build a usable garbage collector. For now I have to stop the experiment or else I may not have anything left for the week for the other projects :(
Maybe 11% was left after a day’s continuous push, but for now safe for 24 hours again :) hopefully the project will be worthy enough after proper release with the correct open source license.
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