←
Thierry Templier581 posts
Thierry Templier avatar

Thierry Templier

@templth

Agents produce everything and remember nothing | Building Relinkia — the context layer you own | Author @ManningBooks, @packtpub, Eyrolles

◷ Joined September 2009▧ 6 Photos and videos
Thierry Templier avatar
Thierry Templier@templth·Aug 19

Count the AI tools you used this month. ChatGPT, Claude, Copilot, Gemini, Perplexity. Now: how many of them know what you were thinking last Tuesday? Zero. Every single one starts from a blank page.

Thierry Templier avatar
Thierry Templier@templth·Nov 12

What "capture" looks like in the Claude app: Claude asks before it writes the updated map to Relinkia over MCP. My notes are in French, the routine is the same in any language.

Post attachment
Thierry Templier avatar
Thierry Templier@templth·Nov 12

7/ The whole routine is one Claude skill, for any subject: github.com/Relinkia/skills/t… It runs on a free Relinkia account, or without Relinkia on a folder of markdown files in Claude Code. You lose versioning and phone access there, the method stays the same.

Thierry Templier avatar
Thierry Templier@templth·Nov 12

5/ When a descent ends I say "capture". Each concept gets a note with the problem it solves, a worked numeric example, why it's used there, common misconceptions, code and three recall questions. A map keeps what I know and where it stops.

Thierry Templier avatar
Thierry Templier@templth·Nov 12

4/ A session starts from an anchor. This week it was a post about JEPA. From my phone I go down one concept at a time: latent space, SIGReg, BatchNorm, LayerNorm, RMSNorm, and finally attention.

Thierry Templier avatar
Thierry Templier@templth·Nov 12

3/ Claude's memory and Projects helped, but pieces went missing and older material came back half rebuilt. Now the reference lives in Relinkia, the tool I'm building, over MCP: every note is versioned, and any session can read it.

Thierry Templier avatar
Thierry Templier@templth·Nov 12

2/ Each new chat started from zero. I re-explained what I already knew, and the reference docs I had asked for were scattered across dozens of old conversations or rebuilt from fragments.

Thierry Templier avatar
Thierry Templier@templth·Nov 12

1/ I'm learning deep learning with Claude, one concept at a time. The explanations are good. What I understood used to disappear when the conversation ended, so I changed how I work. Thread.

Thierry Templier avatar
Thierry Templier@templth·Nov 11

The questions worth asking an AI about your own reading are narrow. Where you contradict what you wrote in 2024, or which of your notes answer each other without you noticing. No prompt gets there without your notes and the links between them.

Thierry Templier avatar
Thierry Templier@templth·Nov 10

Read-later apps keep what you save and note apps keep what you write. The step between reading something and seeing your own field differently because of it is still done by hand, which is why it mostly doesn't happen.

Thierry Templier avatar
Thierry Templier@templth·Nov 6

You rarely notice the day you change your mind. It happens over months, in notes that never sit next to each other, until you argue for something your own notes argued against in March. A tool that reads your notes could show you that March note first.

Thierry Templier avatar
Thierry Templier@templth·Nov 3

Most AI second brain demos run on a corpus picked for the demo and a query tried a dozen times beforehand. For the Relinkia demo, the full corpus rebuilds from public sources with its dates, and the run isn't scripted. If the feature doesn't fire, there's no video.

Thierry Templier avatar
Thierry Templier@templth·Nov 2

Two notes you wrote three years apart may hold the same idea from different angles, and memory alone will never put them side by side. Comparing every note against every other is tedious for a person and cheap for software.

Thierry Templier avatar
Thierry Templier@templth·Oct 29

Paste fifty notes into ChatGPT and it answers from whichever ones happened to fit the question. Point RAG at the raw files and you get quotes back, not the reasons you linked them. What both miss is how your notes relate, and that's written nowhere in the files.

Thierry Templier avatar
Thierry Templier@templth·Oct 26

Most second brains store things very well. A brain keeps less, but it lets an old memory run into a new one, sometimes one that contradicts it. A folder tree never puts two notes in front of each other unless you open both yourself.