“Keep your context window under control.”
— Robert Scoble (@Scobleizer) 19 avril 2026
Uncle Bob always makes me laugh. pic.twitter.com/PB4oKv7QCU
“Keep your context window under control.” Uncle Bob always makes me laugh.
TECHNOLOGY
-
Keep Your Context Window Under Control Uncle Bob
By
–
-
Santiago Bernabéu: World’s Biggest Hidden Robot Stadium
By
–
Santiago Bernabeu: The World’s Biggest Hidden #Robot Stadium
— Ronald van Loon (@Ronald_vanLoon) 19 avril 2026
by @lukas_m_ziegler#EmergingTech #Tech #Technology #TechForGood pic.twitter.com/aOVvh30hcSSantiago Bernabeu: The World’s Biggest Hidden #Robot Stadium
by @lukas_m_ziegler #EmergingTech #Tech #Technology #TechForGood -
Benchmarking quantization levels with TurboQuant for best context fit
By
–
Tried more quants (4-bit, 5-bit) on upstream llama.cpp Next up is benchmarking TurboQuant for the same quants The goal is finding the best quant that fits with the highest context in q8_0/turbo3 asymmetric
-
Knowledge Graphs Transform Modern AI Applications
By
–
Documents into Knowledge: Graphs in Modern AI https://
youtu.be/yyuVR-ML9X8 At the first World's Fair, @emileifrem
, CEO of @Neo4j
, gave one of the most well received @aiDotEngineer talks of all time. He's back now with the 2 year update — now that Context Graphs are cool again, -
Built AI-powered news aggregator using list-based architecture
By
–
It works. I built https://
alignednews.com/ai all on lists -
AI API costs drop 90% enabling scalable data collection
By
–
Building https://
alignednews.com/ai used to cost $400 a day in API calls. To grab 40,000 posts. Monday it should drop to $40 a day to do same -
AGIBOT Unveils Genie G2 Next-Generation Wheeled Humanoid Robot
By
–
AGIBOT Unveils Genie G2: Next-Generation Wheeled Humanoid #Robot
— Ronald van Loon (@Ronald_vanLoon) 18 avril 2026
by @CyberRobooo
#Robotics #EmergingTech #Innovation #Technology pic.twitter.com/g9gfZdXMRzAGIBOT Unveils Genie G2: Next-Generation Wheeled Humanoid #Robot
by @CyberRobooo #Robotics #EmergingTech #Innovation #Technology -
Qwen3.5 9B benchmarked: TurboQuant avoids OOM at full context
By
–
Benchmarked the same Qwen3.5 9B UD-IQ3_XXS GGUF on an RTX 3070 8GB using – Latest upstream llama.cpp VS – TheTom's TurboQuant llama.cpp fork TurboQuant allowed me to reach full context length without OOM, more in the screenshot below
-
Trucks Transformed into Drone Command Hubs via AI
By
–
From Road to Sky: Trucks Transformed into #Drone Command Hubs
— Ronald van Loon (@Ronald_vanLoon) 18 avril 2026
via @ZappyZappy7
#Engineering #ArtificialIntelligence #Innovation #Technology pic.twitter.com/umQdQnwlohFrom Road to Sky: Trucks Transformed into #Drone Command Hubs
via @ZappyZappy7 #Engineering #ArtificialIntelligence #Innovation #Technology -
High IQ Doesn’t Guarantee Wisdom in Tech Career
By
–
What string theory has shown me was that it's possible to have an extremely high IQ AND be a complete idiot. That inisght has served me really well in my tech career.