The next Grok update (internally V7) finished pre training and expected to be natively multimodal with a direct Audio and processing. One shot game generation is expected to get better as well.
PROMPT ENGINEERING
-
Enhancing Medical Reasoning with LLMs: Training and Test-Time
By
–
10. Medical Reasoning in the Era of LLMs This review categorizes techniques for enhancing LLM medical reasoning into training-time (e.g., fine-tuning, RL) and test-time (e.g., prompt engineering, multi-agent systems) approaches, applied across modalities and clinical tasks.
-
Claude System Prompts Evaluation Examples Detailed
By
–
I quote that tweet pretty often! I'm looking for the next level of detail from @AmandaAskell though… I want to see just one example of an actual eval used for the Claude system prompts
-
Optimizing ChatGPT Performance Through Planning and Validation
By
–
By the way, this type of approach is specifically important in ChatGPT because by forcing the model to plan, validate, and think better, you basically have more chances to get the best version of it.
-
GPT-5 vs Claude: Instruction precision and multi-agent routing comparison
By
–
I think GPT-5 is extremely particular about the instructions, while Claude can get around with more ambiguity (also claude code is multi agent).
But if you do it right, GPT-5 is amazing. I'm pretty shocked by the reception, but I really believe this is mostly based on the routing -
GPT-5 Thinking Mode Excels at In-Context Learning
By
–
If you are using GPT-5 in ChatGPT, you should basically never use the regular version, only the thinking one! That one is really good with in-context learning
-
Next AI Model Differentiators in Chained Prompting
By
–
If you ever do a part 2, add “planning + code + live data” in one chained prompt. That’s where I think the next big differentiator between models will emerge.
-
Deep Research provides significantly more information than standard prompt
By
–
Answer is definitely "no". Here's the same prompt in Deep Research – much much more information here! https://
chatgpt.com/share/68980afd
-2d50-800c-b23b-af9b7043f692
… -
Automatic routing versus deep thinking in AI systems
By
–
No, that's if you are "automatically routed", not if you ask to "think deep".
-
Check Which AI Model Processed Your Prompt
By
–
By popular request, you can now check which model ran your prompt by hovering over the “Regen” menu.