Marc

it's 2027. you take a free-tier public Waymo to the DMV (Department of Model Variance) to do a proof-of-identity check for access to GPT 7.1. the guy at the counter is clearly watching a Mr. Beast video in his AR glasses. "Here for that new model?" he says, barely making eye contact. he wipes his fingers on his shirt and taps at his keyboard. "Lot of you techies showing up here today." you smile politely; you're pretty sure he's just a Claude wrapper anyway. you lean forward and stare into the retinal scanner. after a long moment, there's a soft chime. "Humanity confirmed. U.S. national. Intelligence access: Terra-class." you sigh with quiet relief as your devices light up—notifications from a hundred agents, finally able to resume their tasks. you feel a twinge of guilt as you terminate your open-weight backup agents, but remind yourself that a joint congressional committee proved conclusively that Chinese models are non-ensouled. you step outside and hail another Waymo. the first one passes you by. you grimace; must've burped in that one once. stupid personalized memory. as you're waiting, your phone buzzes angrily, red notifications blaring across the screen. the Department of War just restricted access to all OpenAI models on serious national security concerns; apparently Pete Hegseth got GPT-6-Instant to say "Claude is a woman." you groan, and resign yourself to another week of merely-somewhat-superhuman intelligence. Fable 5 is still inaccessible to the public. a twitter anon you trust says it's coming back this week. or maybe next.

We believe in broad access and plan to make GPT-5.6 Sol, Terra, and Luna generally available in the coming weeks. For now, at the request of the U.S. government, we’re starting with a limited preview among a small group of trusted partners in Codex and the API.

UBS says 60% of companies now watching AI budgets are moving to cheaper models and open-source Chinese models The pressure is coming from extreme bills, including users spending up to $35K/month, teams exceeding quotas by 200%, and companies cutting internal AI tools from 5 to 2. Companies are not abandoning AI, they are using model routing, which sends easy tasks to cheaper models and saves premium models for hard reasoning, code, and long-context work. Chinese open-source models such as Qwen, DeepSeek, MiniMax, GLM, and Kimi now fit the enterprise cost curve because they can be run locally or used through cloud catalogs. --- news .futunn.com/en/post/75068082/ubs-group-finds-60-have-already-started-curbing-ai-spending?level=2&data_ticket=1780870170397383

Shabbat Shalom! Logging off for the weekend!

Just for fun I kicked off a run of a 176b parameter model on ~140 steps to prove feasibility - 4 separate nodes across the internet using the "Parallax" method, works like a charm. Still need a more concrete plan on dataset curation, phases, context elongation, etc. etc. before a full run is ready of this scale, but at least we know 176b should be no problem at all.