Just some numbers so you don’t get misled RTX 3090 (7 years old)
> 24GB VRAM
> Bandwidth: 936.2 GB/s
> Bi-directional NVLink 112GB/s RTX PRO 4000
> 24GB VRAM
> Bandwidth: 672 GB/s > No Bi-directional NVLink,
> need 32 Gen. 5 PCIe Lanes to pool 2 at 64GB/s x.com/LLMJunky/statu…
AI
-
RTX PRO 4000 vs RTX 3090 VRAM Bandwidth and NVLink Compared
By
–
-
Assured Robot Intelligence Joins MSL to Build Physical AI
By
–
welcome Assured Robot Intelligence (ARI) to MSL! excited to build physical with @LerrelPinto @xiaolonw and the whole team!
-
OpenAI Codex Introduces Virtual Pets Feature for Users
By
–
ok its not the most important thing we've ever done but i find it more useful than it seems on the surface. check out pets in codex! (and try hatching one)
-
Speculative Decoding Accelerates RL Rollouts 2.5x in NeMo-RL
By
–
RL post-training is hitting a rollout bottleneck. This new paper from #NVIDIAResearch shows how speculative decoding in NeMo-RL + @vllm_project can accelerate rollouts losslessly, with 1.8x higher throughput at 8B and projected 2.5x end-to-end speedup at 235B. Read the full
-
LATAM Airlines Presents Production AI Agents at LangChain Interrupt
By
–
@LATAMAirlines is landing at Interrupt. The largest airline in Latin America built two production agents that handle trip planning and agency coordination. Building them was easy. Operating at scale was the real challenge. At Interrupt, the Agent Conference by LangChain,
-
Claude Code Drains MacBook Battery Fast vs SSH Alternative
By
–
This is something I discovered Claude Code is a battery suck, just a few hours and my MBP 16" M4 is empty, it's crazy SSH'ing into a server you can go all day!
-
Grok 4.3 Arrives on Abacus AI ChatLLM Platform
By
–
Grok 4.3 just landed on ChatLLM by Abacus AI Sonnet-level performance, ~5x cheaper, and faster in real use. Built for sharp reasoning and clean outputs. Worth testing.
-
Run LLMs Locally on Your Own Hardware With RTX 3090s
By
–
re: Anthropic, Dario, OpenAI, etc Don’t let them control your Intelligence Utilization It is a MUST that you learn how to run your LLMs locally on your own hardware 2x RTX 3090s and Qwen 3.6 27B is all you need to get started
-
AI Agents Browsing the Web with DeepAgents and Browserbase
By
–
one future trend i'm very excited by:
— Harrison Chase (@hwchase17) 1 mai 2026
models getting good enough where they can power agents that browse the web
deepagents + @browserbase is a glimpse of that future
See the full example here: https://t.co/RTk0kOY8ML https://t.co/v5lDHiARph pic.twitter.com/7p7UbjkPyHone future trend i'm very excited by: models getting good enough where they can power agents that browse the web deepagents + @browserbase is a glimpse of that future See the full example here: https://
github.com/browserbase/in
tegrations/tree/main/examples/integrations/langchain/deepagents-browserbase
… -
RL Boosts Known Tasks But Causes Hallucinations on Unknown Ones
By
–
RL is a bit of a double edged sword: in known territory performance increases, but in unknown territory the model tends to hallucinate that it is performing a completely different task it was trained on