Moritz Kremb

Agency Builder · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

14statements → 6claims → 2claims resolved → 3.86/5average certainty → 2/5average debate potential →

2 supported 0 partly supported 0 contradicted 4 not checkable as stated how the 6 claims stand · each chip opens the sources

1 prediction · 5 assertions · 1 opinion · 5 insights · 2 disclosures · every statement was checked. The prediction and assertions are the 6 claims: statements the public record can support or contradict. 2 are resolved, and 4 name no date, number or outcome precise enough to check. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Moritz argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Assertion Supported
Moritz Kremb: OpenAI permits OpenClaw OAuth connections while Anthropic officially bans them
“Because OpenAI has stated that they're okay with it. So for them, it's definitely fine to use this OAuth method with Anthropic. It's kind of a gray area a bit. I think officially in their terms of service, it says you're not allowed to do that.”
Moritz Kremb Mar 19, 2026 ▶ 26:42 I fixed OpenClaw so it actually works (full setup)

How they sound: not measured why? →

We measure speaking style by listening to the audio itself, and a fair number needs at least 2,000 words from one person on tape we have measured. There is too little of Moritz Kremb on measured tape to publish a rate. This says nothing about how they speak.

Everything Moritz Kremb said on the Startup Ideas Podcast that made the record, most notable first. Filter by type, assessment or year in the ledger →

Assertion Supported
Moritz Kremb: OpenAI permits OpenClaw OAuth connections while Anthropic officially bans them
“Because OpenAI has stated that they're okay with it. So for them, it's definitely fine to use this OAuth method with Anthropic. It's kind of a gray area a bit. I think officially in their terms of service, it says you're not allowed to do that.”
Moritz Kremb Mar 19, 2026 ▶ 26:42 I fixed OpenClaw so it actually works (full setup)
Assertion Supported
Moritz Kremb: Anthropic is banning users for connecting OpenClaw via OAuth
“And some people have been getting banned over it. So I do recommend that if you, if you're scared about your account getting banned, just create a new one, create a new account and put the 20 dollar plan on that.”
Moritz Kremb Mar 19, 2026 ▶ 27:10 I fixed OpenClaw so it actually works (full setup)
Opinion
Moritz Kremb: OpenClaw is the closest system to a truly autonomous agent
“And so it's kind of the first really personal agent that exists and also Currently, I would say it's the closest to what we have of a truly autonomous agent.”
Moritz Kremb Mar 19, 2026 ▶ 3:01 I fixed OpenClaw so it actually works (full setup)
Insight
Moritz Kremb: Hosting autonomous AI agents locally is safer than cloud VPS
“To mitigate that, I actually recommend just like set it up on a local Mac. Because there the risk is much lower than if you're setting it up on a VPS. Like a VPS is this thing that's in the cloud and it's like constantly connected to the internet. And it's jus…”
Moritz Kremb Mar 19, 2026 ▶ 43:00 I fixed OpenClaw so it actually works (full setup)
Assertion Not checkable as stated
Moritz Kremb: Claude Cowork is just Claude Code with a better UI
“So they kind of built cloud co-work and put that in the app with just a nicer UI. But under the hood, it's basically the same as Cloud Code.”
Moritz Kremb Mar 19, 2026 ▶ 8:33 I fixed OpenClaw so it actually works (full setup)
Prediction Not checkable as stated
Moritz Kremb expects major AI providers to build proprietary OpenClaw clones
“And so what I do expect to happen is that it, like Claude code and Claude co-work and so on, they will all build like their own kind of versions of open claw.”
Moritz Kremb Mar 19, 2026 ▶ 9:30 I fixed OpenClaw so it actually works (full setup)
Assertion Not checkable as stated
Moritz Kremb: Claude hallucinates OpenClaw solutions instead of checking official documentation
“Because normally Claude will, if you ask it something about OpenClaw, it's like, it can give you the right answer, but it often just makes something up. If it doesn't really know, it doesn't always go and check the docs by itself through its web search feature…”
Moritz Kremb Mar 19, 2026 ▶ 13:36 I fixed OpenClaw so it actually works (full setup)
Insight
Moritz Kremb warns users to inspect ClawHub skills for suspicious community instructions
“One thing you should be, you should always be double checking these skills because anyone can create them and there can be like all kinds of instructions inside of these skills. So what actually the creator has done, they've, Like added this security scan here…”
Moritz Kremb Mar 19, 2026 ▶ 37:47 I fixed OpenClaw so it actually works (full setup)
Insight
Moritz Kremb: Stronger frontier AI models natively defend against prompt injection attacks
“Actually the most useful one is to mitigate this risk is just to use a strong model. Because the smarter the model, the better it is actually at like not falling for these prompt injection tricks.”
Moritz Kremb Mar 19, 2026 ▶ 46:45 I fixed OpenClaw so it actually works (full setup)
Insight
Moritz Kremb: Automated AI content machines fail because audiences demand authentic trust
“And I would say nowadays it's really not that hard to just create this content machine that like just pumps out AI slop. But it's not useful at all. Right. Especially in an era AI era you know, where, where trust like is getting lower and lower, your content s…”
Moritz Kremb Mar 19, 2026 ▶ 50:48 I fixed OpenClaw so it actually works (full setup)
Disclosure
Moritz Kremb: Preloading OpenClaw documentation into Claude fixed 99% of errors
“And since I have this it's solved like 99% of my problems.”
Moritz Kremb Mar 19, 2026 ▶ 14:40 I fixed OpenClaw so it actually works (full setup)
Insight
Moritz Kremb: Instruct OpenClaw to update its context files for behavioral feedback
“When you notice something that you want to happen again, or don't want to happen again, just tell your OpenClaw to update these files.”
Moritz Kremb Mar 19, 2026 ▶ 17:33 I fixed OpenClaw so it actually works (full setup)
Assertion Not checkable as stated
Moritz Kremb warns autonomous AI agent API requests can cost $0.20 each
“If you use a model through the API, it can really get very expensive. Like every, every request can be like 20 cents and that can stack up really quickly.”
Moritz Kremb Mar 19, 2026 ▶ 23:11 I fixed OpenClaw so it actually works (full setup)
Disclosure
Moritz Kremb automated his grocery ordering on German service Rewe using OpenClaw
“I've logged into that browser with my, like the, in Germany it's called Rewe. It's like this Instacart basically. And it will start like Ordering my groceries for me essentially and clicking around and ordering my stuff. So I've automated like this whole part …”
Moritz Kremb Mar 19, 2026 ▶ 32:51 I fixed OpenClaw so it actually works (full setup)

Appearances (1)

EpisodeDateSpeaking time
I fixed OpenClaw so it actually works (full setup) Mar 19, 2026 49m
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.