This is what separates casual AI users from power users.. Most prompt for answers. Grok prompts can return strategy level thinking.
LLMS
-
Better answers need better inputs; prompting is the new literacy
By
–
People want better answers. But they don’t give better inputs. Prompting well is the new literacy.
-
Luc Julia Claims GPT-5 Inferior to GPT-3.5
By
–
C’est délirant !
— Docteur Laurent Alexandre (@dr_l_alexandre) 2 septembre 2025
Luc Julia affirme que GPT-5 est moins bon que GPT-3.5
C’est aussi dingue que dire qu’un Airbus est moins rapide qu’une trottinette
Luc Julia ne connaît RIEN au sujet en plus d’avoir menti en faisant croire qu’il avait créé SIRI
pic.twitter.com/rF1je5Ca0WC’est délirant ! Luc Julia affirme que GPT-5 est moins bon que GPT-3.5 C’est aussi dingue que dire qu’un Airbus est moins rapide qu’une trottinette Luc Julia ne connaît RIEN au sujet en plus d’avoir menti en faisant croire qu’il avait créé SIRI
-
Claude as framework executor building systems from structure
By
–
Claude isn’t a chatbot. It’s a framework executor. You feed it structure, it builds systems.
-
OpenAI releases GPT-5 and GPT-5-mini models
By
–
https://
platform.openai.com/docs/models/gp
t-5-mini
… gpt-5-mini lists May 31, 2024 (aka June 2024), https://
platform.openai.com/docs/models/gp
t-5
… gpt-5 lists Sep 30, 2024 -
GPT-5 Release and Multimodal Image Editing LLMs August
By
–
For August it's mainly the release and impact of GPT-5, plus the new wave of image editing multi-modal LLMs represented by Qwen-Image-Edit (open weights) and Gemini Nano Banana Here's the August newsletter table of contents
-
GPT-Realtime Knowledge Cutoff Compared to GPT-4o and GPT-5
By
–
gpt-realtime has a knowledge cutoff date of Oct 01, 2023 – the same date as GPT-4o https://
platform.openai.com/docs/models/gp
t-realtime
… The GPT-5 knowledge cutoff date is Sep 30, 2024, which makes me suspect that gpt-realtime may be a more similar model to GPT-4o than to GPT-5 -
iPhone ChatGPT Voice Mode: GPT-4o versus gpt-realtime models
By
–
Does anyone understand the relationship between iPhone ChatGPT voice mode and the underlying models? Is it still stuck with the old GPT-4o voice model, or is it using the new gpt-realtime model? How does gpt-realtime relate to GPT-5?
-
GLM-4.5 Surpasses Claude Opus in Tool Use Efficiency
By
–
Z AI's GLM-4.5 just dethroned Claude Opus 4 in tool use with nearly 100x lower costs The model scored 70.85 on the Berkeley Function-Calling Leaderboard at just $2.9, while Opus 4 scored 70.36 at a cost of $207.12
-
Tencent Launches Hunyuan World Model and Multilingual Translation System
By
–
Tencent launched two new Hunyuan models:
— The Rundown AI (@TheRundownAI) 2 septembre 2025
—HunyuanWorld-Voyager, an ultra-long-range world model with native 3D reconstruction and memory
—Hunyuan-MT-7B and Hunyuan-MT-Chimera-7B, a joint AI translation system that outperforms rivals across 33 languagespic.twitter.com/NAeOdjGQa4Tencent launched two new Hunyuan models: —HunyuanWorld-Voyager, an ultra-long-range world model with native 3D reconstruction and memory
—Hunyuan-MT-7B and Hunyuan-MT-Chimera-7B, a joint AI translation system that outperforms rivals across 33 languages