Dagens Vibes — 13. juli 2026

Tibo@thsottiaux

Updates for Codex and ChatGPT Work users. No nerfing, only good stuff! - We have landed inference optimizations and are passing down savings to all the subscriptions for GPT-5.6 Sol. That should result in around 10% more usage on its own. - We noticed that by changing the context size limit in the product to 372k for GPT-5.6 Sol, up from 272k for GPT-5.5, it resulted in more usage being charged than intended. We have reverted to 272k and will work to roll back out to 372k in the days to come. You should notice that usage drains significantly less after this change. - To understand where the extra usage was coming from, we ran some experiments where reasoning efforts were changed (referred to as juice values under the hood) and have reverted this. - There is slightly more usage of multi-agent than intended in high and xhigh reasoning effort, we are fixing this going forward. Also fixing a small other thing we noticed with auto-review where we can be more efficient. And we continue to have the 5h limit temporarily not apply. Enjoy the rest of the weekend!

Florian Brand@xeophon

verifiers v1 is finally out, something we worked on for months to nail it properly Lets talk about some of the non-obvious things that these changes unlock:

Sudo su@sudoingX

i said the answer was more interesting than a yes or a no. here it is. left is grok 4.5's build. three minutes, one prompt, cold start, every test green. right is the original, the same scene grok build and i grew over three weeks of iteration. same locked spec on both sides. here's the part that breaks brains: grok 4.5 matched every single number in that spec. 5,200 bark fibres, exactly. 650 stars, exactly. trunk tapering 0.62 to 1.55 over 4.6 units, exactly. the acceptance gate came back 12 for 12. and the scenes still don't look alike. the grass on the left technically exists, 8,000 instanced blades, but the spec never gave a blade height, the model guessed short, and the lawn vanished. the crown clumped upward instead of spreading, because "a rounded ancient crown" is an adjective, not a number. the pond shrank to a smear at the rim. every number transferred perfectly. everything alive in the scene lived in the adjectives. that's the actual state of coding agents in july 2026. speed is solved. correctness is mostly solved. taste is not close. you can hand a model your spec. you cannot yet hand it your eye. i bench agents. this is what the benches are for, finding the exact line between what's solved and what's marketing. all tests green and the world still doesn't feel right. sit with that one.

David Crawshaw@davidcrawshaw

Tricks I use when having an agent code review its own work: - tell it to do the code review in a sub-agent *without* the existing session as context. let it read the commit with fresh eyes - tell it to "favor its original judgement" on small issues - use the other top-end model

Mario Zechner@badlogicgames

recommended reading. terry tao vibe coding.

Pi@pidotdev

And Pi out of the box sends less than 1.2k tokens ;)

elie@eliebakouch

i've been letting fable run experiments (mostly autonomously) to test a few ideas we had about jlens when does the structure form in training? can you transfer between models? how does it scale? how far does a nudge travel? what does K2 jlens look like?