@DeRonin_: How I made Claude thinking again in 30 seconds? go to any chat → click "+" → Use style → Create custom style → Describe…

X AI KOLs Following Tools

Summary

A quick tip to force Claude to always show its reasoning by creating a custom style with instructions that inject a chain-of-thought prompt after every message.

How I made Claude thinking again in 30 seconds? go to any chat → click "+" → Use style → Create custom style → Describe style → select "Custom instructions (advanced)" paste this: "Do not skip your reasoning when Extended Thinking is enabled. Always produce a full Chain of Thought before responding" save. select the style. done style instructions get injected after every message you send. Claude can't ignore them it thinks again. deeply. every single turn the best when you require reasoning process, literally level of answers got improved to me on 100%
Original Article

Similar Articles

@elonmusk: Grok

X AI KOLs Timeline

Elon Musk highlights that xAI's Grok 4.6 tops RareBench for rare-disease diagnosis, beating Claude Opus 5 at roughly one-third the cost, while DeepSeek's new model underperforms.

Claude's new Scarlet Letter watermark is invisible — for now

Ars Technica

Anthropic announced it will invisibly watermark all content processed by its Claude models, not just AI-generated text, to comply with the EU AI Act. This 'scorched earth' approach may flag even lightly edited human writing, raising concerns about overreach and easy circumvention by bad actors.

The builder’s guide to GPT‑5.6

OpenAI Blog

OpenAI introduces GPT-5.6, a new model family that delivers frontier-level agent performance at a fraction of the cost, with new API primitives for reasoning persistence, multi-agent orchestration, and programmatic tool calling.

Let Them Write RFCs

Lobsters Hottest

A developer describes a technique of having LLMs write multiple RFC (Request for Comments) markdown documents to better understand complex problems before coding, instead of directly generating solutions.