FranciscoCarlos

Author here, feel free to ask anything

Still a crutch around incomplete pre-training data, a ton of useful knowledge wont be properly represented on the weights.

Also a great potential indicator on when the pretraining run for the model started.

Willing to scale it up if there's interest

Yeah, it can be worked around with in-context instructions but they still tend to scope, delegate and architect without awareness of the fact that agents exist and work. It's an actual big deal IMHO, opus 5.5 is the most updated AFAIK.

They know it and they try to cover it up with a fake reported cutoff date. Claude reports June '26 but it has only partial 2026 data (tested it against the API and it's 25 as well). GPT refuses to answer but it's old 25 data.

Seems like a rushed RL run on top of an old model to jump into the hype train, seems reasonable since they hold a fantastic distribution moat. Even if it's not SOTA a billion people will use it and they'll collect data-points for future iterations. Same as muse.

How is a model that has never seen an agent on it's pretraining data going to reasonably plan and fan-out tasks to multiple agents? Or engineer software for agents to edit semi-automatically, it has zero awareness of it's capabilities in it's internal representation.

They need to pretrain on fresh data.

Gemini 4 Argon

As of my knowledge cutoff, three of the top state-of-the-art large language models are Google's Gemini 2.5 Pro, OpenAI's o3 (and GPT-4.5), and Anthropic's Claude 3.7 Sonnet.