Reverse Engineer Anything 😂 Software is done.

PS5 is now 80% ported to PC. We might actually get GTA 6 on PC at launch week...

This is my new local inference cluster: 2× NVIDIA DGX Spark 1× NVIDIA Jetson Orin Nano Kubernetes tying it together Not a rack. Not a cloud bill. Just a lot of AI compute on a desk.

Robinhood $HOOD ended August with 28.6M funded customers and $384B in total platform assets, up 8% MoM and 26% YoY. Net deposits reached $4B for the month and $74.1B over the last 12 months, equal to a 24% annual growth rate.

Cybercab is working tirelessly today for a flawless debut. With just six days until the official event, let’s keep pushing all the way to the finish line!

Most production inference services run on Kubernetes, where declarative configuration helps coordinate distributed services. Running one inference server in a Slurm job is easy; running a production-style topology across multiple containers and nodes is not. NVIDIA’s open-source srt-slurm (github.com/NVIDIA/srt-slurm) provides a YAML-based orchestration layer for these deployments. It coordinates sbatch and srun, GPU placement, networking, readiness checks, and cleanup for systems involving prefill/decode disaggregation, multiple workers, Dynamo frontends, KV-cache-aware routers, and KV-cache offloading services. It’s useful for quickly deploying representative inference systems for testing or benchmarking on GPU clusters that already run Slurm. Great work to @0xishand and the rest of the @NVIDIAAI team on this!

all roads lead back to vertical sidebars.

slack is the new ide

vLLM hit new peak bs=1 decode on Kimi-K3: 464 tok/s 🚀 Under a low-entropy reasoning workload, Kimi-K3 + DSpark on vLLM reaches 464 tok/s on batch size 1 with 4×4 GB300. This benchmark is fully reproducible with public image: vllm/vllm-openai:kimi-k3 and @inferact's DSpark draft model linked in the thread. 1/3

This is my new local inference cluster: 2× NVIDIA DGX Spark 1× NVIDIA Jetson Orin Nano Kubernetes tying it together Not a rack. Not a cloud bill. Just a lot of AI compute on a desk.

This is my new local inference cluster: 2× NVIDIA DGX Spark 1× NVIDIA Jetson Orin Nano Kubernetes tying it together Not a rack. Not a cloud bill. Just a lot of AI compute on a desk.

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time. I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!