what is agent looping
for the last two years we prompted agents one task at a time. that is starting to change
instead of asking an agent to build the landing page and then driving every step yourself, you set up a loop that handles discovery, planning, the work, checking, and iterating until the goal is met
looping is a setup you build. almost any agent harness can run it, it just depends on how you wire it up
at its simplest, looping is one agent working on itself:
> researches
> drafts
> checks the draft against a goal
> fixes what is weak
> runs that cycle again until the work clears the requirements
you are not prompting each step anymore. the agent repeats the cycle for you
the bigger version is a fleet looping. you give an orchestrator agent a goal, it breaks the goal into pieces, hands each piece to a specialist agent, and those specialists hand smaller jobs to their own subagents
the whole tree keeps looping through discovery, planning, execution, and verification until the goal is met
one agent looping is like a person redoing their own draft. a fleet looping is a whole team running a project end-to-end
you create a goal, and the system runs the loop until it finishes within the reqs you set
open and closed looping:
OPEN LOOPING is exploratory. it still has conditions and a goal, but you give the agent or the fleet a wide space to move in. it can try different paths, discover things, build something you did not fully spec out
this is the exciting end, it is what Peter and others are doing, and tbh it is where I want to spend more time
the catch is cost, an open loop with real room to explore burns an insane amount of tokens. for the 90 percent of people without an unlimited budget it is not runnable yet, and pointed at projects with a loose standard it turns into a slop machine
CLOSED LOOPING is bounded. a human designs the end-to-end path first:
> clear goal
> defined steps
> an eval at each step
> a point where it stops or hands back to you (and feeds back performance data)
the agents still loop, but inside framework you built. it gets better every run because each pass feeds the next, and it runs on a normal budget because the path is tight.
for most marketing work, closed is the one that pays off today.
> the orchestrator owns the goal
> the specialists own the steps
> the subagents do the narrow work
> an eval gate make sure its not slop
"Just write loops" confuses people. There are two kinds:
/goal runs until a condition is true, then stops. "get this @threejs scene to 60fps on mobile." It profiles, fixes, remeasures, and repeats on its own until it hits the number, then hands back.
/loop runs indefinitely on a schedule. "every 5 min babysit my PRs: fix broken CI, rebase, handle new review comments." If PRs keep coming in, it never finishes. It just keeps watching.
Both Claude Code and Codex ship both (automations). You stop writing prompts and start writing the finish line (goal) or the heartbeat (loop).
@DSchloemp23@TenbaggerAktien Nach 15 Tagen kommen die ganze Nachfrageschocks der Indizes, die Zwangseinkaufen müssen ;-) wenn ein Kursrutsch kommt, dann voraussichtlich im Dezember wenn die Lockup Zeit für Mitarbeiter etc vorbei ist
@DSchloemp23@TenbaggerAktien Nach 15 Tagen kommen die ganze Nachfrageschocks der Indizes, die Zwangseinkaufen müssen ;-) wenn ein Kursrutsch kommt, dann voraussichtlich im Dezember wenn die Lockup Zeit für Mitarbeiter etc vorbei ist
The scary part about Anthorpic's Fable nerf is not that it refuses to answer biology or cryptography. It's that it foreshadows what's coming. A world where a couple companies decide what you can and cannot do. They're building a new ruling class and you're not in it...
Sleep is the most powerful medicine on Earth.
It boosts memory, recovery, fat loss, and even helps with anxiety.
Here’s how to improve it with 7 simple steps:
1. Don’t sleep 8 hours.
It's basically a timer that wakes up the agent and gives it information / instructions.
Instead of starting a new session and saying "you are X, you do Y, you have access to Z".
You can take an existing session and give it that in a loop.
You can use it for lots of things, like monitoring information, monitoring progress, deciding to act based on what it sees, etc.
Practical example, i have one agent who is responsible for deciding to modify the main code base. Every 10 minutes, it will check to see if there's a pull request that passes all gates to be merged to main. If it does, it merges it, if not, it says why it didn't merge it, then goes back to sleep, and waits for the next 10mn. It does from "/loop every 10mn check the PR queue and do your job according to merge-master.md"
"Books are the closest thing you’ll ever come to finding cheat codes for real life. You can access the entire learnings of someone else's career in a few hours." —@tobi
Als der Erste Weltkrieg begann, brauchte Großbritannien dringend Geld für den Krieg. Deshalb gab die Bank of England im November 1914 eine Kriegsanleihe über 350 Millionen Pfund aus.
Die Bürger sollten investieren und den Krieg unterstützen. Die Nachfrage fiel jedoch viel geringer aus als erwartet. Statt 350 Millionen kamen nur etwa 91 Millionen Pfund von echten Investoren zusammen.
Um das nicht wie einen Fehlschlag wirken zu lassen, griff die Bank of England selbst ein. Über eigene Funktionäre kaufte sie große Mengen der Anleihen auf. Nach außen wirkte die Ausgabe dadurch deutlich erfolgreicher, als sie tatsächlich war.
Kurz zuvor hatte Großbritannien den Goldstandard ausgesetzt. Dadurch konnte die Regierung deutlich mehr Geld in Umlauf bringen und den Krieg leichter finanzieren. Während des Krieges funktionierte das zunächst. Die Folgen zeigten sich später.
Nach dem Ende des Krieges stiegen die Preise stark an. Zwischen 1919 und 1920 kam es zu einer massiven Inflation von bis zu 20 %.
Für viele Menschen verloren ihre Ersparnisse dadurch einen großen Teil ihres Wertes. Geld, das über Jahre zurückgelegt worden war, hatte plötzlich deutlich weniger Kaufkraft.
Die Geschichte zeigt, wie Regierungen und Zentralbanken in Krisenzeiten handeln, wenn der Druck groß genug wird. Die Rechnung zahlen am Ende oft die Bürger, wenn Inflation ihr Vermögen entwertet.
Banken und Regierungen meinen es nicht gut mit uns Bürgern. Das war schon immer so und wird immer so bleiben.
@brannoseth@sparbuchfeinde Sizilien kam mir gesitteter vor, Region um San Vito zumindest. Sardinien Überholvorgang in der Kurve fast normal, egal ob Ostküste, Nordküste oder Inland. Wenn in der Kurve keine reifen quietschen, wird gedrängelt und in den ungünstigsten Situationen überholt
With all of the exploits in DeFi, Zcash, and all of the other insanely complex crypto systems we are reminded again that Bitcoin’s simplicity is its biggest feature.
Recap — 8 daily fixes for 3 AM wake-ups:
1. No food 3h before bed
2. 9 PM open-loop dump
3. Map vs territory check
4. Name the primal loop
5. 4-8 breathing before bed
6. 'What does my body feel?' at 3 AM
7. Stop willpower-ing back to sleep
8. One true thing before sleep
Germany is the world’s greatest builder of industrial champions.
Germany alone accounts for roughly 46% of the world’s hidden champions — more than any other country.
Highly specialised, mostly mid-sized firms that rank among the top 3 globally in their niche markets or #1 in Europe.
These are not famous consumer brands. They are the companies producing the machines, components, tools, industrial systems and precision technologies behind global supply chains.
Even after the 2022 energy crisis and years of industrial pressure, Germany’s current-account surplus was still around 4.5% of GDP in 2025 — roughly €203 billion — the largest in the world after China.
This is why Germany became Europe’s strongest export economy: not only because of giants like BMW, Siemens or Volkswagen, but because thousands of specialised German firms became global leaders in extremely specific industrial markets.
@sephthreek@ThorstenPolleit Anstatt DCA einfach mal größere Einzelkäufe machen? DCA macht v.a. dann Sinn imo, wenn der Bullenmarkt losgeht. Im Bärenmarkt entweder Einzelkäufe oder Sparplansumme nach oben drehen besser.
Rendite ist Schmerzensgeld, die mutigen werden (eher) belohnt
https://t.co/btNzl2nYKd
@RobLennister@PhilippMattheis 1. I had fear
2. Banks weren't defaulting
3. Paused my ETF savings plan 1 month ago to stack more cash I can throw at the market