Doesn't work though… one error almost immediately, another two when you try to close. Never shows the app nor its content.
@alexjc
-
Environment Learns Back: Adaptive Tools for Agent Learning
By
–
The Environment Learns Back! "tools that adapt to an agent's local mistakes, using cheap computation and simple forms of learning" creative.ai/blog/env-learns-…
-
New Scaling Law Discovered for LFM2.5-350M Overtraining
By
–
That new LFM2.5-350M is super overtrained, right? And everyone was shocked about how far they pushed it? As it turns out, we have a brand new scaling law for that! 🧵 [1/n]
-
Nvidia Eyes Model Serving at 10,000-20,000 Tokens Per Second
By
–
Nvidia's Chief Scientist Bill Dally says there's a path to serving relatively large models at 10,000 to 20,000 tokens per user per second.
— Marcelo P. Lima (@MarceloLima) 4 avril 2026
For context, Opus 4.6 is ~43 and Grok 4.2 Beta is ~251 tokens/user/s 🤯 pic.twitter.com/mbZNFfWgUbNvidia's Chief Scientist Bill Dally says there's a path to serving relatively large models at 10,000 to 20,000 tokens per user per second. For context, Opus 4.6 is ~43 and Grok 4.2 Beta is ~251 tokens/user/s 🤯 [Translated from EN to English]
-
GitHub’s Explosive Growth: 14 Billion Commits Projected for 2026
By
–
Kyle Daigle (@kdaigle) Yup, platform activity is surging. There were 1 billion commits in 2025. Now, it's 275 million per week, on pace for 14 billion this year if growth remains linear (spoiler: it won't.) GitHub Actions has grown from 500M minutes/week in 2023 to 1B minutes/week in 2025, and now 2.1B minutes so far this week. So we're pushing incredibly hard on more CPUs, scaling services, and strengthening GitHub’s core features. And as a fine purveyor of hand-crafted shit code for many years, I'm not gonna weigh in on that. 🤣 — https://nitter.net/kdaigle/status/2040164759836778878#m
-
Slopsquatting: AI Hallucinations Enable New Supply Chain Attack
By
–
URGENT PSA – New supply chain attack vector that I found WILD > AI LLMs hallucinate package names roughly 18-21% of the time.
— Basel Ismail (@BaselIsmail) 2 avril 2026
Hackers have started pre-registering those hallucinated names on PyPI and npm with malicious payloads; they call it "slopsquatting"
You can only imagine… pic.twitter.com/wyPwHE9NT5URGENT PSA – New supply chain attack vector that I found WILD > AI LLMs hallucinate package names roughly 18-21% of the time. Hackers have started pre-registering those hallucinated names on PyPI and npm with malicious payloads; they call it "slopsquatting" You can only imagine what's next Community note: The 'slopsquatting' attack vector was documented as early as April 2025 and not newly discovered. The cited 18-21% package hallucination rate applies to open-source LLMs; commercial models average 5.2% according to the referenced study using pre-2025 models. socket.dev/blog/slopsquat… arxiv.org/pdf/2406.10279
-
Neural Cartography: Real-time Mapping Engine with Distributed Agents
By
–
Neural Cartography – a real-time city mapping engine powered by distributed rendering agents
— SHAHNAB AHMED (@AhmedShahnab) 1 avril 2026
Agents work in parallel. City name gets drawn in the center. Urban fabric assembles around it.
The idea behind Neural Cartography – a WebGL visualization where 7 specialized agents are… pic.twitter.com/5L7NYhvTFENeural Cartography – a real-time city mapping engine powered by distributed rendering agents Agents work in parallel. City name gets drawn in the center. Urban fabric assembles around it. The idea behind Neural Cartography – a WebGL visualization where 7 specialized agents are dispatched simultaneously to reconstruct any city from raw geospatial data, tracing roads, waterways, railways, and city boundaries in real-time – right in your browser. #CreativeCoding #ThreeJS #ReactThreeFiber #DataVisualization #Geospatial #AgenticAI @reactthreefiber @threejs #builders [Translated from EN to English]
-
ReSplat: Learning Recurrent Gaussian Splatting Code Released
By
–
🚀 Excited to release the code and models of ReSplat: Learning Recurrent Gaussian Splatting!
— Haofei Xu (@haofeixu) 31 mars 2026
🌐 Project page: https://t.co/OB38xC7hu4
💻 Code & models: https://t.co/xGCsiZc9YD pic.twitter.com/HkrMdDKJ2N🚀 Excited to release the code and models of ReSplat: Learning Recurrent Gaussian Splatting! 🌐 Project page: haofeixu.github.io/resplat/ 💻 Code & models: github.com/cvg/resplat
-
EGO-BIRD: 100,000 Hours of Bird Footage for Autonomous Drones
By
–
after the overwhelming support for EGO-SNAKE, i’m excited to share EGO-BIRD
— Tejes Srivalsan (@tejessrivalsan) 29 mars 2026
100,000 hours of pov bird footage to train the next generation of autonomous drones pic.twitter.com/YLiNYOM444after the overwhelming support for EGO-SNAKE, i’m excited to share EGO-BIRD 100,000 hours of pov bird footage to train the next generation of autonomous drones
-
Three-month-old Anthropic model achieves SOTA on code maintainability
By
–
~3mo old model is still SOTA and was +8% vs 5.3-codex on maintainability total anthropic victory Gabe Orlanski (@GOrlanski) We found that agents generate progressively worse code with each iteration. Real developers do not. SlopCodeBench is the only eval that faithfully measures quality degradation on iterative, long-horizon coding tasks. arxiv.org/abs/2603.24755 scbench.ai 🧵 — https://nitter.net/GOrlanski/status/2037560777356238881#m