The .20 update has a few system prompt improvements that improve reliability across all models. Working on it!
LLMS
-
Comparing AI Model Capabilities Across Different Conversation Sessions
By
–
Did you do this in the same conversation as a prior gen?
-

School maze worksheet with blue pen solution and ChatGPT Images 2.0
By
–
"School worksheet with maze, 32 wide by 48 tall, rows and columns numbered, no unreachable rooms, solution in blue pen, name field reads 'ChatGPT Images 2.0' in cursive at top" Note the fusion of code and imagegen this task requires.
-

OpenAI’s GPT-image shows significant quality leap on leaderboards
By
–
Holy! I did not expect OpenAI’s GPT-image to be such a big jump in quality and leaderboards. OpenAI was cooking. Makes me even more excited for spud
-

Claude Code director explains agent workflow and improvement system
By
–

The director of Claude Code shared his workflow He explains how he plans complex tasks, divides work with subagents, a continuous improvement system based on errors, and much more Here it is for you to save
-
Model Weights Alone Reveal Identity Without System Prompts
By
–
To head off the obvious question: This was conducted via the API and so it should not have hidden memory/system prompts/etc which leak the identity of yours truly to the model. The model weights, alone, got it to enough information.
-
Claude Opus Identifies Writer by Stylistic and Biographical Tells
By
–
Opus' rationale for the one it got right begins with the accurate and somewhat disconcerting "RATIONALE: Several strong stylistic and biographical tells point to Patrick McKenzie."
-
Claude Opus 4.7 Reproduces Writing Samples in Informal Test
By
–
FYI, I casually tried to reproduce this on three writing samples from many years ago, which I do not believe to be on the public Internet and which were varying subjective difficulty levels. Opus 4.7 went 1 for 3 with ~no effort in the prompt (~two sentences long).
-
Meta’s JEPA Strategy Shift: LLM Focus Over World Models
By
–
Right. Except that Mark Z, @boztank and others in the leadership were always supportive of the JEPA / World Models project as a long-term bet.
But the AI strategy of company became more LLM-pilled and short-term focused.
And many of the applications of JEPA/WM are in industrial -
ColBERT Memes Trend Takes Over Social Media Timeline
By
–
My timeline is full of ColBERT memes. How did that happen?