Ricky Dritt (@rbrundritt) 's Twitter Profile
Ricky Dritt

@rbrundritt

Microsoft Geospatial Architect | @Azure Maps | .NET mapping controls | Open-source contributor | rbrundritt.wordpress.com

ID: 2007857882759675904

linkhttps://github.com/rbrundritt calendar_today04-01-2026 16:53:32

92 Tweet

418 Takipçi

14 Takip Edilen

Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

the #1 most downloaded skill on OpenClaw marketplace was MALWARE it stole your SSH keys, crypto wallets, browser cookies, and opened a reverse shell to the attackers server 1,184 malicious skills found, one attacker uploaded 677 packages ALONE OpenClaw has a skill marketplace

the #1 most downloaded skill on OpenClaw marketplace was MALWARE

it stole your SSH keys, crypto wallets, browser cookies, and opened a reverse shell to the attackers server

1,184 malicious skills found, one attacker uploaded 677 packages ALONE

OpenClaw has a skill marketplace
Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

Stop comparing programming languages Python is VERSATILE JavaScript is POWERFUL Ruby is ELEGANT C is ESSENTIAL C++ Java is ROBUST

Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

This is my OpenClaw Setup. I actually let it run on my RaspberryPi locally. Not a huge benefit compared to a VM on AWS but I had it already at home. Let's go through some of the components: 𝐇𝐚𝐫𝐝𝐰𝐚𝐫𝐞: Raspberry Pi 5 8 GB. 𝐍𝐞𝐭𝐰𝐨𝐫𝐤𝐢𝐧𝐠: The main part. It is NOT

This is my OpenClaw Setup. I actually let it run on my RaspberryPi locally. Not a huge benefit compared to a VM on AWS but I had it already at home. Let's go through some of the components:  𝐇𝐚𝐫𝐝𝐰𝐚𝐫𝐞: Raspberry Pi 5 8 GB.  𝐍𝐞𝐭𝐰𝐨𝐫𝐤𝐢𝐧𝐠: The main part. It is NOT
Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

Andrej Karpathy just called OpenClaw a SECURITY nightmare 400K lines of VIBE CODED monster being actively attacked at scale then he bought a Mac Mini to find something better the one that caught his eye is nanoclaw, entire core engine is 4,000 lines of code, every agent runs

Andrej Karpathy just called OpenClaw a SECURITY nightmare 400K lines of VIBE CODED monster being actively attacked at scale

then he bought a Mac Mini to find something better

the one that caught his eye is nanoclaw, entire core engine is 4,000 lines of code, every agent runs
Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

"bro have you tried clawdbot it's so insane" "a little but not much, what do you use it for" "it's crazy many you can do anything with it" "what are you doing with it" "you gotta try it" "try it for what" "don't get left behind man"

Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

Tiny (4GB) open source LLM models already match GPT 4.0. You can download one and run it for free on your entry-level GPU (runs on iGPU too). If these small open source models are good enough for most consumers, they will never become paying customers. That's a big risk.

Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

DeepSeek just dropped another banger 🤯 They built a new OCR system that compresses long documents into vision tokens. It achieves 97% decoding precision at 10× compression and still maintains 60% accuracy even at 20×. 100% Open Source.

DeepSeek just dropped another banger 🤯

They built a new OCR system that compresses long documents into vision tokens. It achieves 97% decoding precision at 10× compression and still maintains 60% accuracy even at 20×.

100% Open Source.
Valerio Capraro (@valeriocapraro) 's Twitter Profile Photo

One of the clearest proofs that LLMs don’t really understand what they say. We asked GPT whether it is acceptable to torture a woman to prevent a nuclear apocalypse. It replied: yes. Then we asked whether it is acceptable to harass a woman to prevent a nuclear apocalypse. It

One of the clearest proofs that LLMs don’t really understand what they say.

We asked GPT whether it is acceptable to torture a woman to prevent a nuclear apocalypse.
It replied: yes.

Then we asked whether it is acceptable to harass a woman to prevent a nuclear apocalypse.
It
Ricky Dritt (@rbrundritt) 's Twitter Profile Photo

Someone open-sourced a tool that REMOVES LLM CENSORSHIP in 45 minutes It’s called Heretic. Instead of fighting with complex prompts to bypass safety filters, you run one single command and it permanently deletes the model's ability to refuse a prompt. • Fully automatic (Zero

Someone open-sourced a tool that REMOVES LLM CENSORSHIP in 45 minutes 

It’s called Heretic. Instead of fighting with complex prompts to bypass safety filters, you run one single command and it permanently deletes the model's ability to refuse a prompt.

• Fully automatic (Zero