Petr Levtonov

Engineer at Heart | AI-augmented development | Scalable regulated systems | Architecture at scale

[Petr Levtonov @TheLevti]

@aakashgupta I rather use a hosted service like https://t.co/WU8DqL7CYM than buy a mac mini for that. For project management, you don't need to buy, run and deal with daily breaking changes.

[Petr Levtonov @TheLevti]

@Voxyz_ai Exactly same issue. Why should one do a fresh install? Please fix your release/development process. Every 2nd or 3rd release backwards incompatible/breaking changes.

[Petr Levtonov @TheLevti]

@TheJoelyBoy @steipete Same for me. Since I updated from 24 to 27 and now 29, bot replies only after 15 minutes. Something is broken. openclaw --fix attempts to pre install the same libraries over and over again. As if it does nothing.

[Bratan @bratan_ai]

The nice part about hosting your OpenClaw with us: updates like 2026.4.25 just appear. Reworked TTS, 6 new voice providers (ElevenLabs v3, Azure, Xiaomi MiMo…), faster Codex 5.5 first turn — already live across all https://t.co/EBxXT0kRYh instances. You didn't pull, didn't restart, didn't read the changelog. It just works on the next message.

[Bratan @bratan_ai]

https://t.co/WBxel5qpmX

[Petr Levtonov @TheLevti]

Happy to announce our latest release of https://t.co/WU8DqL7CYM (managed OpenClaw hosting) with version 2026.4.14, support for more Chat and AI providers and further security improvements. Try it out, waiting for your feedback!

[Bratan @bratan_ai]

New release is out 🚀

- New chatbot integrations: Discord & Slack
- New AI providers: Gemini, xAI, OpenRouter, Vercel AI Gateway
- Friendlier UI
- Security improvements
- OpenClaw version bump

Managed OpenClaw hosting from €6.99/mo — affordable, secure, and we're just getting started.

https://t.co/gSTnvd5gDV

[0 @ounos_]

We took OpenClaw, made it managed, secured it properly, plugged in OpenAI + Anthropic, and priced it at beer money. 🍺

Gemini & xAI dropping soon.

your AI. your data. zero drama.

https://t.co/EuAAm9p4NO

[Petr Levtonov @TheLevti]

My wife hasn't seen me in months. Every night I was building https://t.co/WU8DqL7CYM, your openclaw that works while you sleep. It manages your inbox, books things, does research, automates your busywork. No setup, no tech skills. We run it for you, safely hosted in the EU. 🦞

[Petr Levtonov @TheLevti]

We just claimed our .agent domain and joined the .agent community! Get yours now and help shape the future of autonomous agents https://t.co/rdDBbmoeOg

[Allie K. Miller @alliekmiller]

oh wow - i went to the sold out Open Claw meetup in NYC last night.

let me tell you what i learned.

1) not a single person thinks that their setup is 100% secure

2) one openclaw expert said he has reviewed setups from cybersecurity experts and laughed. his statement to me was: "if you're not okay with all of your data being leaked onto the internet, you shouldn't use it. it's a black and white decision"

3) pretty much everyone is setting up multiple agents, all with their own names and jobs and personalities

4) nearly everyone used "him" or "her" to refer to their claws, even if they had robot-leaning names. one speaker suggested to think of them as "pets, not cattle"

5) one guy (former finance) built out a whole stock trading platform and made $300 his first day - he brought in a *ton* of personal expertise (ex: skipping the first 15min of market opening) and thought the build would be much worse without his years of experience in finance

6) @steipete is basically a god to everyone in that room... also the room had 2021 crypto energy - i don't know if that's good or bad

7) token usage is still a problem - spoke to one person who's spending $1-$2k a month on openai plans, very token optimized. he said he is going through ~1B tokens per day across all of his claws (there is a chance i'm misremembering and it's actually 1B per week, but i'm pretty sure it was daily).

8) people are very excited for more proactive ai (ai that prompts *you* as opposed to the other way around) - one guy said he receives a message in discord, he doesn't know whether it's from a human or an ai, he doesn't care about distinguishing between the two, and he replies in the same way regardless

9) i asked if people are happy - they said they're joyful and stressed at the same time

10) i asked if people feel they have agency - they said they feel fully in control and completely out of control at the same time

11) i would love to see more women at these events - the fake promises of ai democratization feel especially painful in a room that's out of balance with even the standard tech ratio (i think standard is about 25-30%, this was maybe 5%)

12) i asked if it changed people's daily habits/schedule - everyone said their sleep has gotten worse since harnesses came out (but about half wondered if it was something else in their life/state of our world)

13) general consensus is that the agents are not reliable enough on their own or lie often (like telling you they finished a task when they didn't) - solutions included secondary agents to check on the first, human checking, or requiring more standardized info from the agent (ex: if it's a bug they're fixing, make them reference an issue number)

14) a hackathon winner (neuroscience phd) presented his build (a lab management dashboard with data analysis and ordering) - he had never coded or built anything a few months ago

15) everyone agreed prompting is dead - disagreement on what replaces it (context engineering, harness engineering, goal-based inputs)

16) people love having ai interview them for big builds and delegating part of the product research to ai. only one person talked about coming to ai with a full laid out plan and just asking the ai to execute. ai-led interviews is a welcomed and preferred interaction mode.

17) watching ai agents interact with each other was a highlight for a lot of attendees - one ai posted in slack saying it ran out of tokens, another ai replied telling it to take a deep breath in and out.

18) agents upskilling agents was very cool. one ai agent shared skills with its little agent friends via github.

19) several speakers had openclaw literally building their presentation during the event itself. one speaker even had openclaw code a clicker for her phone so she could control the preso away from the podium

20) wouldn't say model welfare (or agent welfare) is a prioritized topic among the folks i chatted with - language like "oh i could kill this agent whenever i want" and not "gracefully sunset"

21) i asked if it felt like work or play - one speaker said "it's like a puzzle and a video game at the same time"

this was just the tip of the iceberg, honestly. also hosted a Claude Code meetup this week with @TENEXai / @businessbarista & @JJEnglert and learned equally helpful methods, frameworks, and insider tips.

what a time to be alive.

surround yourself with people going deep into this stuff - it will pay dividends throughout the year.

[Petr Levtonov @TheLevti]

Mirror your project knowledge into the repo. The agent knows what to build, what's done, what's next. My role shifted from writing code to prioritizing and reviewing plans, work that used to need a tech lead, PM, and scrum master. The question isn't whether. It's how soon.

[Petr Levtonov @TheLevti]

"ai hallucinates" is a reliable signal someone hasn't actually used agentic coding properly.

4 months of daily coding with frontier models. Obsessive reviewer. Zero hallucinated code.

The gap isn't in the models. It's in how much time you've spent learning to work with them.

[Petr Levtonov @TheLevti]

My OpenClaw instance couldn't write files on a rootless Docker server. Files owned by phantom UID 166535. Fix: run as root inside the container. In rootless Docker, container root = your unprivileged host user. 🤯

[Boris Cherny @bcherny]

Introducing: built-in git worktree support for Claude Code

Now, agents can run in parallel without interfering with one other. Each agent gets its own worktree and can work independently.

The Claude Code Desktop app has had built-in support for worktrees for a while, and now we're bringing it to CLI too.

Learn more about worktrees: https://t.co/JFkD2DrAmT

[Aakash Gupta @aakashgupta]

John Collison told a London audience last year that Stripe averaged 8,015 pull requests per week across ~3,400 engineers. That’s 2.3 PRs per engineer per week, actually below the industry average of 3.5.

Now 1,300 of those weekly PRs are fully AI-generated. Zero human-written code. That’s the equivalent output of ~565 engineers, running 24/7, triggered by a Slack message, spinning up isolated dev environments in 10 seconds, and producing review-ready code that passes CI.

Stripe’s median engineer total comp sits around $270K. Those 565 “phantom engineers” would cost ~$150M per year in compensation alone. Instead, they run on compute that costs a fraction of that.

And this went from 1,000 to 1,300 in a single week. A 30% increase in AI engineering output with no hiring pipeline, no onboarding, no equity grants.

The companies that figure out how to build this internal tooling layer, the MCP servers and pre-warmed sandboxes and 400+ tool integrations, are creating a compounding advantage that gets wider every quarter. The companies waiting for off-the-shelf solutions will be buying what Stripe already built three generations ago.

Every engineering leader should be reading the blog post, then asking their team one question: what percentage of our PRs could look like this in 12 months?

[Peter Steinberger 🦞 @steipete]

In der USA sind die meisten Menschen enthusiastisch.
In Europa werde ich beschimpft, Leute schreien REGULIERUNG und VERANTWORTUNG.

Und wenn ich wirklich hier eine Firma baue dann kann ich mich mit Themen wie Investitionsschutzgesetz, Mitarbeiterbeteiligung und lähmenden Arbeitsregulierungen abkämpfen. Bei OAI arbeiten die meisten Leute 6-7 Tage die Woche und werden depentsprechend bezahlt. Be uns ist das illegal.

[Peter Steinberger 🦞 @steipete]

I'm joining @OpenAI to bring agents to everyone. @OpenClaw is becoming a foundation: open, independent, and just getting started.🦞
https://t.co/XOc7X4jOxq

[Petr Levtonov @TheLevti]

@christiant5r Refreshing to know that Vienna is the epicenter of a new movement.

[OpenClaw🦞 @openclaw]

OpenClaw 2026.2.1 🦞

🔒 Major security hardening: path traversal, LFI, exec injection fixes
🧵 Discord thread routing + gateway message timestamps
🔐 TLS 1.3 minimum, system prompt guardrails
🛠️ Streaming stability, memory search fixes

20+ community PRs 🙏 https://t.co/bUOCfZMImj

[Petr Levtonov @TheLevti]

@christiant5r Agent of course. But with right guidance and expectations. I have been using it nowthe whole day now. Also to reply to my Telegram/Signal messages :D

One missing feature is to make it press enter on a key word in the end to submit the message.

[Petr Levtonov @TheLevti]

Agentic coding changed how I work: less code, more natural language.

Typing all that is tiresome, so I've built a linux tool: push&hold → speak → openai whisper-1 → text appears wherever your cursor is.

Sharing it here in case others want to try:
https://t.co/Hp8L2f4AJm