In Stavanger, Gudbjørg Simonsen turns downsizing into a design advantage, trading excess for integrated storage and rigorously edited furnishings. The result is calm, not clutter.
https://t.co/N70w9OEgGc
He built a trading bot on Polymarket with Claude
Result: +$154,263 in 2 months
His bot trades short-term crypto Up/Down markets using a high-frequency algorithm built around 3 elements:
1. Uses limit orders
2. Identifies market direction with its own probability model
3. Buys both sides of the market to manage directional exposure
His Polymarket username: std0
Using directional trading, partial market making, and clean execution, he consistently grows his capital
Anthropic just released a playbook for prompting Claude Fable 5. Most people still use it like older Claude models and get average results.
Here are the 5 shifts that turn it into a compounding system.
First, give it a simple markdown notes file. It reads lessons from every run at the start of the next session - what worked, what failed, voice tweaks, CTA strength. This builds memory across sessions.
Second, always include the "why." Fable 5 needs context on intent, constraints, and goals. Without it, the model guesses and stalls on decisions. With it, it pauses only for destructive actions or scope changes and keeps shipping.
Third, keep prompts short. Over-engineering with old Claude 4.0 skills and rigid rules actually degrades output. Start fresh, let it think for itself.
Fourth, Fable runs autonomously for hours or days by design. Use the effort dial: Low/Medium for quick tasks, High as default for real work, XHigh for non-negotiable quality, Ultracode for full orchestration.
Five, treat every session as part of a memory system. Reference prior notes, audit claims, and let it compound.
The result: proactive agents that expand scope 4x without hand-holding.
Fable 5 rewards trust, not control.
CLAUDE CODE + OBSIDIAN IN UNDER 1 MINUTE
The trick is not “AI note taking.”
It is giving Claude Code a place where your thinking already has structure.
The video’s setup is simple:
download Obsidian,
put your notes in one vault,
keep them as local .md files,
then connect that vault to Claude Code through the Obsidian CLI.
Now your notes stop being a pile of old thoughts.
They become files Claude can read like a codebase.
Project notes can connect to meeting notes.
Ideas can connect to goals.
Open loops can connect to old decisions.
Then the useful part starts: custom commands.
A /today command can pull calendar context, tasks, recent notes, and active projects into one prioritized plan for the day.
An /emerge command can scan across months of notes and surface the ideas you keep circling but never clearly named.
That is the actual workflow:
Obsidian stores the thinking.
Claude Code operates on the thinking.
Commands turn it into repeatable output.
The caveat is obvious but important:
this only works if the vault has signal.
Random clipped articles, messy dumps, and half-written fragments will produce messy answers.
But if your vault has meetings, decisions, goals, tasks, project context, and recurring problems, Claude Code gets much more useful.
Stop asking it isolated questions in a blank chat.
Give it your thinking substrate.
Then make it run commands on top of it.
Earlier today, I was delighted to receive a phone call from Prime Minister Nikol Pashinyan.
Congratulated him and his party on their victory in the recently held Parliamentary elections in Armenia. Thanked him for facilitating the evacuation of Indian nationals stranded in Iran following the recent developments in West Asia.
We reaffirmed our shared commitment to further strengthen our warm and multifaceted partnership across key sectors, including trade, defence, technology and people-to-people ties. We look forward to working closely together to take India-Armenia relations to new heights.
@NikolPashinyan