Fresh stories
Briefs forMay 11
Top storiesthis week
DFlash adds Qwen3-8B speculator with 82.2% first-token acceptance
Posts said Qwen3-8B now has a DFlash speculator with 82.2% first-token acceptance and 3.74 accepted tokens per step, alongside broader DFlash claims of over 6x lossless acceleration. It matters because the release turns a decoding paper into a concrete speculative-inference artifact engineers can test against existing Qwen stacks.
Local users report DeepSeek V4 Flash, Qwen 3.6, and Gemma 4 at 40-200 tok/s on Macs and 3090s
Developers posted new local-model measurements for DS4, Qwen 3.6, and Gemma 4: about 40 tok/s on an M3 Ultra, 70+ tok/s on MacBooks with MPS, and 120-200 tok/s for Qwen3.6-27B on a single RTX 3090. The numbers suggest coding-capable local runs are moving from demos toward regular use.
OpenCode adds Ring 2.6 1T with 256K context and free limited-time access
OpenCode made Ring 2.6 1T available in the editor with reasoning enabled and free access for a limited period. Follow-on posts from Kilo and others claim frontier-level results on AIME 26, ClawEval, Gaia2-search, and Tau2-Bench Telecom.
Gemma 4 MTP benchmarks 138 tok/s in llama.cpp on M5 Max
Community ports brought Gemma 4 multi-token prediction into llama.cpp and MLX Swift, with one M5 Max report moving from 97 to 138 tok/s and another showing 30-40% faster decoding. The gains extend MTP into local runtimes used for on-device coding and long-context work.
OpenRouter launches Pareto Code with min_coding_score tiers and Nitro routing
OpenRouter released Pareto Code, which routes requests to the cheapest coding model above a chosen score threshold and can re-rank for speed with Nitro. Use the API to trade cost against latency with benchmark-based routing controls.
Daily AI Digest
Get the best stories delivered
to your inbox
Skills Spotlighttop by stars
comfyui
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
hyperframes
Create HTML-based video compositions, animated title cards, social overlays, captioned talking-head videos, audio-reactive visuals, and shader transitions using HyperFrames. HTML is the source of truth for video. Use when the user wants a rendered MP4/WebM from an HTML composition, wants to animate text/logos/charts over media, needs captions synced to audio, wants TTS narration, or wants to convert a website into a video.
kanban-orchestrator
Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.