Michal Maciejewski

409 posts

Michal Maciejewski banner
Michal Maciejewski

Michal Maciejewski

@maciejewskii0

20, AI & Software Engineer, documenting my journey.

Frankfurt on the Main, Germany Entrou em Temmuz 2020
623 Seguindo197 Seguidores
Tweet fixado
Michal Maciejewski
Michal Maciejewski@maciejewskii0·
OpenClaw + vibe coding = AI agents that actually ship. Built vibe-swarm: you text your OpenClaw agent → it spawns Codex/Claude Code in tmux+git → they write code & open PR → auto reviews (Codex + Claude Code + Gemini + screenshot gate) → fail? agent respawns with failure context, retries 3x → all green → ping on Telegram → you merge. No dashboards, no cloud. Just bash, tmux, GitHub. @steipete github.com/maciejewskii/v…
English
1
1
10
1.4K
Michal Maciejewski
Michal Maciejewski@maciejewskii0·
@AlexFinn running my entire life on cron jobs and wondering why it's slow is peak openclaw
English
0
0
0
8
Alex Finn
Alex Finn@AlexFinn·
IF YOU'RE ON OPENCLAW DO THIS NOW: I just sped up my OpenClaw by 95% with a single prompt Over the past week my claw has been unbelievably slow. Turns out the output of EVERY cron job gets loaded into context Months of cron outputs sent with every message Do this prompt now: "Check how many session files are in ~/.openclaw/agents/main/sessions/ and how big sessions.json is. If there are thousands of old cron session files bloating it, delete all the old .jsonl files except the main session, then rebuild sessions.json to only reference sessions that still exist on disk." This will delete all the session data around your cron outputs. If you do a ton of cron jobs, this is a tremendous amount of bloat that does not need to be loaded into context and is MAJORLY slowing down your Openclaw If you for some reason want to keep some of this cron session data in memory, then don't have your openclaw delete ALL of them. But for me, I have all the outputs automatically save to a Convex database anyway, so there was no reason to keep it all in context. Instantly sped up my OpenClaw from unusable to lightning quick
English
195
102
1.7K
233.5K
NotebookLM
NotebookLM@NotebookLM·
We wanted to come on here to clear the air and confirm that the rumors are true... Cinematic Video Overviews are officially rolled out to 100% of Pro users in English! Please respect our privacy during this time by flooding our replies with your favorite creations.
English
122
132
2.4K
159.7K
Naive
Naive@usenaive·
Introducing Naive - hire autonomous employees with their own identity. Own compute. Own bank account. Own legal entity. Own email. Own credentials. Own mobile. No humans-in-the-loop. They sign up for tools, pay for services, deploy apps, file documents, and run your entire company. Describe a business. Naive runs it. Reply "Naive" + RT. Get $100 credit for free.
English
723
447
1.8K
134.1K
Michal Maciejewski
Michal Maciejewski@maciejewskii0·
google ai studio launched full-stack vibe coding this week and it's different from what you're thinking the actual stack: describe app → gemini builds frontend + backend + db + auth → deploys to firebase + cloud run → remembers project context between sessions why it matters vs bolt/lovable/replit: - database is real firebase, not fake json - auth works from day one - project memory persists across sessions you get something closer to a working system, not just a demo that breaks when you actually use it concrete takeaway: for prototyping something this week, this is now faster than writing boilerplate yourself what's your go-to for quick prototypes right now?
English
0
0
1
36
ThePrimeagen
ThePrimeagen@ThePrimeagen·
google is one of the most advanced and most inept companies at the same > buy the original company and develop webp in 2010 > in 2026 still do not support it in youtube thumbnails > if user literally renames *.webp -> *.png it works > same thing in google docs
English
56
54
2.9K
98.8K
Kalshi
Kalshi@Kalshi·
JUST IN: Elon Musk says the AI winners will be: • Google in the West • China on Earth • SpaceX in space
English
159
173
3.6K
234.2K
Wes Bos
Wes Bos@wesbos·
Composer 2 vs Opus 4.6 vs GPT 5.4 - a totally unscientific test > Create a Twitter clone. Use Better Auth, Vite, Sqlite, Drizzle, Typescript, and React with Tanstack Start. Each one took ~5 mins in plan mode. Each had access to a browser to test. Composer: 5 mins $6.04 1,250 LOC Opus: 19 mins $10.43 1,000 LOC GPT: 22 mins $14.15 2,000 LOC Opus seems to use the cache WAY more than composer, so it's not really 10x more expensive. Composer app ran first try. Other two needed a bit of CORS debugging but did work. Code between all was extremely similar All three done inside cursor - so Claude Code / Codex may have been different Models used: Composer 2.0 (regular, not fast) Opus 4.6 Medium Thinking GPT 5.4 Medium Thinking
Wes Bos tweet mediaWes Bos tweet media
Wes Bos@wesbos

Cursor just launched Composer 2 - their own model. It's 10× cheaper than Opus 4.6 and supposed to rival it. I've been using it for a few days, I don't have any skewed graphs to show you but from a pure vibes POV I can tell you it's pretty good™ My litmus test right now is if it can build a 3D Printable model with Manifold CAD. I build a Gif zoetrope generator and it did fantastic.

English
59
27
749
184.8K
Michal Maciejewski
Michal Maciejewski@maciejewskii0·
The AI coding wars, this week: → Claude Code hit $2.5B revenue run-rate → Google paid $2.4B for Windsurf, absorbed team into DeepMind → OpenAI bought Astral (uv + ruff) to power Codex → Cursor dropped Composer 2 Everyone is betting everything on who writes the code.
English
1
0
3
104
François Chollet
François Chollet@fchollet·
This is more evidence that current frontier models remain completely reliant on content-level memorization, as opposed to higher-level generalizable knowledge (such as metalearning knowledge, problem-solving strategies...)
Lossfunk@lossfunk

🚨 Shocking: Frontier LLMs score 85-95% on standard coding benchmarks. We gave them equivalent problems in languages they couldn't have memorized. They collapsed to 0-11%. Presenting EsoLang-Bench. Accepted to the Logical Reasoning and ICBINB workshops at ICLR 2026 🧵

English
130
256
2.4K
194.8K
Elon Musk
Elon Musk@elonmusk·
@bindureddy Google will win the AI race in the West, China on Earth and SpaceX in space
English
825
791
7.1K
884.5K
Bindu Reddy
Bindu Reddy@bindureddy·
Gemini 3.0 didn’t quite work out and most of us are still stuck with 2.5 Sometimes I don’t get it - what’s preventing Google from ditching all the side hustles and training 100 models from 100 teams in parallel Pick the model/team combination that produces a decent model! That way, they will at least stay in the AI race 😅
English
124
45
871
205.3K
laurence
laurence@functi0nZer0·
Claude, repair the LNG facilities before market open, make no mistakes
English
104
1.7K
22.7K
586.5K
Fastbreak Hoops
Fastbreak Hoops@FastbreakHoops5·
When a 74-year-old man got called out in a New York courtroom for using an AI lawyer without telling the judge 😭
English
196
1.1K
16.7K
2.2M

Descobrir

@itsolelehmann @AutismCapital @AlexFinn @stolinski @NotebookLM @usenaive @cgtwts @tufpraise