Exactly, they actually opened up the model and research, which the "Open" company didn't, and merely adjusted some of their pricing tiers to try to combat commercially (but not without mumbling something like "yeah, we totally had these ideas too"). Now every single Meta, OpenAI etc engineer is trying to copy DeepSeek's innovations, and their first act is to... complain about copyright infringement, of all things?! What an absolute clown party, how can these people take themselves seriously, do they just have zero comprehension of what hypocrisy is or what's going on here...
I can scarcely process all the levels of irony involved, the irony-o-meter is pegged and I can't get the good one from the safe because I'm incapacitated from laughter.
Altman was in a bit of a tricky position in that he figured OpenAI would need a lot of money for compute to be able to compete but it was hard to get that while remaining open. DeepSeek benefit from being funded from their own hedge fund. I wonder if part of their strategy is crack AI and then have it trade the markets?
The last (only?) language model OpenAI released openly was GPT-2, and even for that the instruction weighted model was never released. This was in 2019. The large Microsoft deal was done in 2023.
I can scarcely process all the levels of irony involved, the irony-o-meter is pegged and I can't get the good one from the safe because I'm incapacitated from laughter.