Chris Poensgen

We’re doing Builders Night in Berlin again next week: Thu, 26 Feb, 18:00. Building & demos; this time with build tracks + technical security input. Last week we had 400 sign-ups, founders from pre-seed to IPO and OSS maintainers with 100k+ GitHub stars. luma.com/n9sigsgn

"Make no mistakes DO NOT HALLUCINATE. YOU ARE AN EXPERT SOFTWARE ENGINEER"

@juristr working on something similar, more focus on plan mode though 😇 usecentel.com

It's coming together...

@HamelHusain building something similar and launching this week. would love to see you try it too :)

Excited to try this

@birdabo it always was

coding isn’t the hard part anymore. distribution is.

@pranaveight the dev environment is going to vanish completely

What rethinking the dev environment from first principles is starting to look like (i'm biased)

@levelsio @garrytan @TermiusHQ @Hetzner_Online typing on terminus is horror though

@garrytan It's @TermiusHQ + Mosh + regular SSH to my @hetzner_online VPS via Tailscale Then I just installed Claude Code on there and code on my sites via that!

Man I need to set this up for all those times it is impolite to have a laptop around lmao

@steipete @ebukagaus not for long

@ebukagaus Not sure if you are joking or not, but there'a big difference between a thoughtful conversation with an agent, then it writing code, then testing it and "yo fix issue x and submit yolo"

Are you a Grifter??

@steipete is your title dev rel?

First project I I was involved in shipping! 🚢 Free token, API credits and security scanner for hard working open source maintainers.

@nbaschez Working on a solution as well, happy to exchange ideas!

If you feel like you are way out ahead of your team in terms of AI adoption, pls DM me, I would love to help

@slobkebap @SarthiB7 sun is shining take a scooter

@SarthiB7 What a SHIT show the last two days have been, wow

Berlin today due to strike

@idosal1 @tobi this is amazing

AgentCraft v1 is live ⚔️ Control your agents like it's an RTS game! It's early. It's rough. It's fun. npx @idosal/agentcraft

@SIGKITTEN @georgepickett yep did the same, spawn sandboxes with modal it’s crazy

codex app-server is legit af i was just looking into it for a project and accidentally ended up making an actual native codex iphone app i can spawn and talk to codexes anywhere on my network and one of the best parts... I built and linked codex into the actual iphone app and it now runs locally on the actual iphone gl doing that, cc

@steipete @buildtheweb1 you could open a openclaw shop with merch

@buildtheweb1 you know just like me that this won't happen.

Hey @steipete, Apple should definitely give you a percentage of the Mac Mini sales since you’ve contributed to them for the last months.

@hasantoxr /new ?

🚨BREAKING: Microsoft Research + Salesforce just dropped a paper that should scare every AI builder. They tested 15 top LLMs GPT-4.1, Gemini 2.5 Pro, Claude 3.7 Sonnet, o3, DeepSeek R1, Llama 4 across 200,000+ simulated conversations. Single-turn prompt: 90% performance. Multi-turn conversation: 65% performance. Same model. Same task. Just... talking normally. The culprit isn't intelligence. Aptitude only dropped 15%. Unreliability EXPLODED by 112%. → LLMs answer before you finish explaining (wrong assumptions get baked in permanently) → They fall in love with their first wrong answer and build on it → They forget the middle of your conversation entirely → Longer responses introduce more assumptions = more errors Even reasoning models failed. o3 and DeepSeek R1 performed just as badly. Extra thinking tokens did nothing. Setting temperature to 0? Still broken. The fix right now: give your AI everything upfront in one message instead of back-and-forth. Every benchmark you've seen was tested on single-turn prompts in perfect lab conditions. Real conversations break every model on the market and nobody's talking about it.

@steipete @openclaw story beats reality any time

The funniest take is that I "failed" 43 times when people look at my GitHub repos and projects. Uhmm... no? Most of these are part of @openclaw, I had to build an army to make it useful. github.com/steipete/

@tibo_maker typing is over anyways 🤷‍♂️

me: gets a scratch from a piece of paper and afraid I could never type on a computer ever again these guys: clearing the chalet with their bare hands at 2x speed

@levelsio tmux + tailscale + terminus app?

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as @marckohlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to @steipete who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by @RichardAtCT on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@steipete @MarcTerns maybe turn of x notifications too

@MarcTerns My thoughts are that I need a break. 1000 pings a day are unmanageable.

Large Slack workspaces hitting rate limits & disconnects with OpenClaw. I just added an optional Slack rateLimitPolicy that avoids slow users.list pagination and lets targeted calls succeed faster. Would love yout thoughts @steipete github.com/openclaw/openc…

@Austen this is the most addictive product since tiktok

I don’t think we fully understand the psychological effects of AI yet. Software work went from slow and methodical and careful to instant gratification all the time. I feel like I’m gonna blow a gasket in my nervous system. Slot machines are nothing compared to this.