Helped a couple troubleshoot their OpenClaw setup today. Nothing beats seeing those happy, excited faces when they birth their Openclaw 🦞🦞
The first pilot gave us some great data on the friction points, so we've refined the whole workflow for the next round.
Catch the next workshop on
28 April if you need some guidance to create your first AI employee!
https://luma.com/htvx3vuo
The first pilot gave us some great data on the friction points, so we've refined the whole workflow for the next round.
Catch the next workshop on
28 April if you need some guidance to create your first AI employee!
https://luma.com/htvx3vuo
❤7
Save this list down and install these skills for Claude to help you cut down on token usage
👇👇👇
1) Plugins / Skills (extend what Claude can do)
👉 https://github.com/obra/superpowers-lab
Based off the OG superpowers skills, this one adds more experimental features to also help you cut down on token usage
2) Memory (Claude remembers things for you)
👉 https://github.com/thedotmack/claude-mem
Think of this like giving Claude a brain that doesn’t reset every time.
Instead of re-explaining your project, style, or preferences every session… it remembers.
⸻
3) Context Manager (only show Claude what matters)
👉 https://github.com/Sceleratis/claude-code-stuff/tree/main/plugins/context-manager
Right now, most people dump everything into Claude. This tool filters and feeds only the relevant parts.
⸻
4) Smart Search (Claude can “look up” your code instead of loading all of it)
👉 https://github.com/danielbowne/claude-context
Rather than loading your whole project into memory, Claude searches and pulls only what’s relevant.
👇👇👇
1) Plugins / Skills (extend what Claude can do)
👉 https://github.com/obra/superpowers-lab
Based off the OG superpowers skills, this one adds more experimental features to also help you cut down on token usage
2) Memory (Claude remembers things for you)
👉 https://github.com/thedotmack/claude-mem
Think of this like giving Claude a brain that doesn’t reset every time.
Instead of re-explaining your project, style, or preferences every session… it remembers.
⸻
3) Context Manager (only show Claude what matters)
👉 https://github.com/Sceleratis/claude-code-stuff/tree/main/plugins/context-manager
Right now, most people dump everything into Claude. This tool filters and feeds only the relevant parts.
⸻
4) Smart Search (Claude can “look up” your code instead of loading all of it)
👉 https://github.com/danielbowne/claude-context
Rather than loading your whole project into memory, Claude searches and pulls only what’s relevant.
GitHub
GitHub - obra/superpowers-lab: Experimental skills for Claude Code Superpowers - new techniques and tools
Experimental skills for Claude Code Superpowers - new techniques and tools - obra/superpowers-lab
❤3
Finally wrote something long-form
First Substack post is up - ParentOS.
It's about using agentic AI for young families: inbox aggregators that catch school logistics before they become arguments, educational agents with guardrails that actually hold, and why you should never build this on an app someone else controls.
Born out of a YouTube Kids incident that happened last weekend.
https://hosanxiv.substack.com/p/parentos-an-idea-i-cant-stop-thinking
First Substack post is up - ParentOS.
It's about using agentic AI for young families: inbox aggregators that catch school logistics before they become arguments, educational agents with guardrails that actually hold, and why you should never build this on an app someone else controls.
Born out of a YouTube Kids incident that happened last weekend.
https://hosanxiv.substack.com/p/parentos-an-idea-i-cant-stop-thinking
Substack
ParentOS: An Idea I Can’t Stop Thinking About
Ideas on Agentic AI for Families with Kids
❤6🔥1
Google is developing a Claude cowork competitor. Will be interesting to see how they catch up
https://www.timesofai.com/news/googles-vision-for-an-autonomous-ai-agent/
https://www.timesofai.com/news/googles-vision-for-an-autonomous-ai-agent/
Telegram now allows your main bot to manage other bots! Goodbye botfather.
- Faster setup (no manual BotFather steps)
- Easier to run multiple bots (one per agent, strategy, or use case)
- Cleaner scaling if you’re running a lot of bots
Check it out here:
https://core.telegram.org/bots/features#managed-bots
- Faster setup (no manual BotFather steps)
- Easier to run multiple bots (one per agent, strategy, or use case)
- Cleaner scaling if you’re running a lot of bots
Check it out here:
https://core.telegram.org/bots/features#managed-bots
🔥1
https://x.com/bcherny/status/2044847848035156457
Tips for Opus 4.7
Enable Auto Mode (Shift-Tab in CLI or dropdown) - No need for --dangerously-skip-permissions anymore. Run long complex tasks (refactoring, research, features) without babysitting or constant prompts — safe auto-approval for most commands.
Use /fewer-permission-prompts skill: Scan session history and add safe repeated commands to your allowlist to reduce interruptions.
Leverage Recaps & Focus Mode (/focus): Quick session summaries when returning + hide intermediate steps to see only final results
Tune Effort Level: Set to xhigh for most work, max for hardest tasks (/effort) for better intelligence vs speed.
Tips for Opus 4.7
Enable Auto Mode (Shift-Tab in CLI or dropdown) - No need for --dangerously-skip-permissions anymore. Run long complex tasks (refactoring, research, features) without babysitting or constant prompts — safe auto-approval for most commands.
Use /fewer-permission-prompts skill: Scan session history and add safe repeated commands to your allowlist to reduce interruptions.
Leverage Recaps & Focus Mode (/focus): Quick session summaries when returning + hide intermediate steps to see only final results
Tune Effort Level: Set to xhigh for most work, max for hardest tasks (/effort) for better intelligence vs speed.
X (formerly Twitter)
Boris Cherny (@bcherny) on X
Dogfooding Opus 4.7 the last few weeks, I've been feeling incredibly productive. Sharing a few tips to get more out of 4.7 🧵
Codex users, try this out
gives you more aesthetic front-end websites instead of the usual AI website templates.
https://github.com/Leonxlnx/taste-skill
gives you more aesthetic front-end websites instead of the usual AI website templates.
https://github.com/Leonxlnx/taste-skill
❤1
https://x.com/ohryansbelt/status/2045873788051415287
if you are using vercel, pls rotate your .env keys.
if you are using vercel, pls rotate your .env keys.
X (formerly Twitter)
Ryan (@ohryansbelt) on X
Someone on BreachForums claiming to be ShinyHunters is selling what they say is Vercel's internal database, access keys, and source code for $2M. ShinyHunters is a black-hat hacker group known for a significant number of breaches and a "pay or leak" model.…
The AI Burrow 🐰🕳️
https://x.com/ohryansbelt/status/2045873788051415287 if you are using vercel, pls rotate your .env keys.
sunday night - becoming tech support 😭😭😭
The AI Burrow 🐰🕳️
https://x.com/ohryansbelt/status/2045873788051415287 if you are using vercel, pls rotate your .env keys.
TL;DR: Vercel Security Incident report by the CEO
• A hacker got into Vercel after an employee’s work account was compromised through another AI tool (context.ai)
• The attacker was highly sophisticated, significantly accelerated by AI accessed some internal systems but customer data impact was very limited.
• Vercel is now tightening security, adding new tools, and telling everyone to update their secret keys.
Feels like someone got early access to Mythos.. I don’t think we are ready for what’s to come
https://x.com/rauchg/status/2045995362499076169?s=46
• A hacker got into Vercel after an employee’s work account was compromised through another AI tool (context.ai)
• The attacker was highly sophisticated, significantly accelerated by AI accessed some internal systems but customer data impact was very limited.
• Vercel is now tightening security, adding new tools, and telling everyone to update their secret keys.
Feels like someone got early access to Mythos.. I don’t think we are ready for what’s to come
https://x.com/rauchg/status/2045995362499076169?s=46
X (formerly Twitter)
Guillermo Rauch (@rauchg) on X
Here's my update to the broader community about the ongoing incident investigation. I want to give you the rundown of the situation directly.
A Vercel employee got compromised via the breach of an AI platform customer called https://t.co/xksNNigVfE that…
A Vercel employee got compromised via the breach of an AI platform customer called https://t.co/xksNNigVfE that…
OpenAI’s latest GPT-Image-2 vs Nano Banana 2.
Looks like an huge jump.
They’ve started rolling it out in phases. Have you manage to try it out yet?
https://x.com/old_pgmrs_will/status/2045379349399101707
Looks like an huge jump.
They’ve started rolling it out in phases. Have you manage to try it out yet?
https://x.com/old_pgmrs_will/status/2045379349399101707
❤1
https://x.com/alchainhust/status/2046192558666342720?s=46
The chinese reversed engineered Claude design, open source and usable with Any model, out tomorrow!
The chinese reversed engineered Claude design, open source and usable with Any model, out tomorrow!
X (formerly Twitter)
花叔 (@AlchainHust) on X
我逆向了Claude Design！
明天12:00正式免费开源Huashu Design，这是预告片👇
明天12:00正式免费开源Huashu Design，这是预告片👇
https://x.com/weezerOSINT/status/2046170666131669027
If you’ve used lovable, be careful.
with a free account someone was able to access all your source code, database credentials, Ai chat history and customer data. the funny part is that it was reported > 1 month ago and still not fixed.
If you’ve used lovable, be careful.
with a free account someone was able to access all your source code, database credentials, Ai chat history and customer data. the funny part is that it was reported > 1 month ago and still not fixed.
X (formerly Twitter)
impulsive (@weezerOSINT) on X
Lovable has a mass data breach affecting every project created before november 2025.
I made a lovable account today and was able to access another users source code, database credentials, AI chat histories, and customer data are all readable by any free…
I made a lovable account today and was able to access another users source code, database credentials, AI chat histories, and customer data are all readable by any free…
Had a dream last night… woke up and decided to build something 😆
Inspired by Mirofish — calling this one Deepfish 🐋
TLDR:
Spun up synthetic agents to simulate how hot-button issues ripple through different segments of Christians in Singapore.
What it does:
Introduce “shock” scenarios (politics, culture, etc.)
Observe how different groups react, reinforce, or push back
Track how sentiment shifts across the system over time
Archetypes:
15 distinct voice profiles
Crossed with 4 theological archetypes
Across 4 generations (Gen Z → Boomers)
Profiles loosely grounded in real-world data (conversations, forums, news)
Stack:
Borrowed from MiroFish + Shark (agent orchestration)
Python + Next.js
Openrouter/Deepseek as Model API
What I’m exploring:
How rhetoric + local pressures (TFR, housing, cost of living) reshape the overall “sentiment map” - not just individually, but collectively.
Still tuning the model, but already seeing some interesting second-order effects 👀
Also made it modular so I can port it over in the future for work related stuff.
Inspired by Mirofish — calling this one Deepfish 🐋
TLDR:
Spun up synthetic agents to simulate how hot-button issues ripple through different segments of Christians in Singapore.
What it does:
Introduce “shock” scenarios (politics, culture, etc.)
Observe how different groups react, reinforce, or push back
Track how sentiment shifts across the system over time
Archetypes:
15 distinct voice profiles
Crossed with 4 theological archetypes
Across 4 generations (Gen Z → Boomers)
Profiles loosely grounded in real-world data (conversations, forums, news)
Stack:
Borrowed from MiroFish + Shark (agent orchestration)
Python + Next.js
Openrouter/Deepseek as Model API
What I’m exploring:
How rhetoric + local pressures (TFR, housing, cost of living) reshape the overall “sentiment map” - not just individually, but collectively.
Still tuning the model, but already seeing some interesting second-order effects 👀
Also made it modular so I can port it over in the future for work related stuff.
❤4🔥2👀2
The AI Burrow 🐰🕳️
OpenAI’s latest GPT-Image-2 vs Nano Banana 2. Looks like an huge jump. They’ve started rolling it out in phases. Have you manage to try it out yet? https://x.com/old_pgmrs_will/status/2045379349399101707
X (formerly Twitter)
Mark Kretschmann (@mark_k) on X
GPT-Image-2 is rolling out right now to all ChatGPT accounts. @OpenAI
Try it it right now in @ChatGPTapp. It's pretty great, although the resolution is unfortunately quite low.
Enjoy ! 🫡
Try it it right now in @ChatGPTapp. It's pretty great, although the resolution is unfortunately quite low.
Enjoy ! 🫡