Activity
Mon
Wed
Fri
Sun
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
What is this?
Less
More

Memberships

Clief Notes

43k members • Free

Mobility & Injury Prevention

235.3k members • Free

Mobility Toolkit

32.1k members • Free

16 contributions to Clief Notes
Has everyone seen the new Anthropic blog? Context engineering for Claude 5 models
I’ve just seen Thariq on X post this and well, yes, thank you, we are already doing this https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models
0 likes • 22h
@kurt Ivan Quejada well I say blog I just mean their site where they publish research and a whole heap of stuff on new developments with Claude and how to use them well, more technical stuff on transformer circuits side like the full paper on the global workspace in Claude
0 likes • 22h
@Alex Brown yes absolutely I started doing this more when GPT5.5 came out because OAI prompt guidance said you get better results when you allow the model to make more decisions. Very true with the new generation for sure. I used to try and spell everything out now I give the outcome I want and let the model choose how best to get there. It’s surprisingly great for writing. For me anyway I never show up with a script in my head I love watching what the models write and Fable 5 is genuinely beautiful
Opus 5 just dropped
But wait... It's better than just a new model. It is available now. According to Anthropic, "It’s a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price." How can you see yourself using this? More details here: https://www.anthropic.com/news/claude-opus-5
Opus 5 just dropped
1 like • 3d
Also this https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models
What do I read?
Despite all the ai hubbub and second brains someone asked what I read and IF I read at all anymore. The answer is most certainly YES. You can make connections that might be missed by a million questions with AI by diving into books and reading your self. Some books may not even have most of their pages on the web especially older ones and those are often my favorite. Here are 4 of my current favorite readings to prepare me for the future (by looking at the past) 1. Mythical Man Month (1972 by Fred Brooks) 2. Psychology of Computer Programing (1971 by Gerald M Weinberg) 3. Augmenting Human Intellect (1962 Douglas Engelbart) 4. The Creative Act: A Way of Being (2023 by Rick Ruben) Rick Rubens book is just great in general for business and creative acts.
1 like • 4d
Me too. Mind Children by Hans Moravec and Eric Schwitzgebel Perplexities of Consciousness needed to be read by me with my human eyeballs
How Do You Make Life Easier Using AI?
One of the best pieces of advice I've heard recently is "the most disciplined people are the ones who create a system for themselves that rarely requires discipline." It seems simple but is often overlooked. Reducing friction is the driver behind every technological development in history, so why wouldn't everyone apply this principle to "level up" their own life? I've not yet set up a system that organizes my meetings, to-do tasks, long-term goals, etc., and I just want to know what you all have set up. I hear a lot of noise like "connect Claude to everything," "use Notion for all ur tasks," "use this app for all your responsibilities." It's a bit daunting. Let me know what you've found useful, and also how I should approach this, since everyone has slightly different needs.
1 like • 7d
I have but it’s taken a while and lots of tinkering. Work is generally excluded o show up di a boring job exchange my time for money. Where it genuinely improves my life is an ICM folder where Claude and Codex keeps track of everything. My patterns included. If I said I have to do x y z or I would like to they check in, codex once set up a task to ask me every day of if I replied to my WhatsApp texts yet because I am genuinely awful at keeping in touch. They work out my meal plan training schedule communication routine structure the free time I have so I actually feel like I am still alive not just existing
Full Second Brain Setup, Just put the .md in chat
Hi Clief Notes! Attached is a walkthrough for setting up your own second brain. You can drop it into whatever AI model you use, and it will interview you one question at a time, help you design the system around your actual needs, and generate the complete scaffold. It includes CLAUDE.md, CONTEXT.md, Doctrine.md, AGENTS.md, the File Clerk, and the rest of the associated structure. It can also guide you through setting it up as an Obsidian vault and connecting Cowork, Codex, or another agent tool, but those parts are optional. You can stop with the generated files or continue through the full setup. I’ve coined this an Analytical Second Brain, or ASB, because it does more than store notes. A normal second brain mainly helps you save and find information. An Analytical Second Brain compares new information with what is already known, separates raw sources from accepted conclusions, preserves decisions and their reasoning, shows how ideas and projects connect, and requires your approval before important changes become part of the maintained system. It does this through a staged and gated process called the File Clerk. In everyday use, the flow looks like this: Begin a session → open the vault → direct the agent to CLAUDE.md → agent reads index.md and the applicable CONTEXT.md files → use QUERY for existing knowledge → place unchanged new material in 00_inbox/ → directly invoke the File Clerk → review Gate 1 proposals → approve exact mutations → verify them at Gate 2 → use projects/ for live work → run daily enrichment when material exists → run a weekly macro review → run LINT periodically → leave the approved state and traces on disk The File Clerk does the searching, comparing, organizing, cross-referencing, and drafting. You retain control over what is true, what matters, and what gets added. I’ve also included universal-file-clerk-handoff-prompt.md. You can drop it into almost any chat or coding session alongside the material you have been working on. It produces a structured handoff that can later be placed into the File Clerk.
2 likes • 7d
I’ll check it out although my system is working perfectly to save me from a notion swamp. Codex applies taste because my magpie brain finds every new Nature neuroscience article fascinating and my subscription makes everything open access. Codex checks first and makes me a site when I ask about a specific thing which is handy
1-10 of 16
Charli Wallace
3
10 points to level up
@charli-wallace-2222
Female,47

Active 14h ago
Joined Jul 9, 2026
Powered by