Cactus launched Needle 3, a foundation model small enough to run as a single 8-29MB binary on phones, wearables, robots, smart home hubs and cars. Built on what the company calls a Simple Attention Network, it sacrifices general chat ability to specialize in three tasks: text embedding for local search, structured data extraction from messy text, and tool calling that maps spoken requests to app functions. The company claims it outperforms models ten times larger on mobile tool calls and matches models two to three times bigger on extraction.
cactuscompute.com
· 2026-09-18
A follow-up experiment tested four open models—DeepSeek V4 Flash, Inkling, Kimi K3, and Qwen3.8 A95B—by inserting the first 1% of GPT-5.5 Pro's reasoning trace into each model's own reasoning channel before letting it generate answers freely. Researchers then measured how much of GPT-5.5 Pro's visible answer text overlapped with each model's output. Qwen3.8 showed the largest jump, with overlap rising from 33.92% unprefilled to 54.50% with the GPT-5.5 Pro prefill, a 20.58 percentage-point increase, while other models showed much smaller shifts.
gist.github.com
· 2026-09-09
The developer behind the iMessage AI assistant Olly, which has processed over 18 million messages with roughly a third routed through OpenRouter's open-source models, published a technical breakdown of problems encountered at scale. The core issue: OpenRouter can send identical model requests to any of about 20 different hosting providers, each running the same weights but with different precision, optimizations and tool parsers, producing measurably different benchmark results. For DeepSeek V4 Flash, GPQA Diamond and TAU-Bench Airline scores varied by several points across providers on the same day.
mmoustafa.com
· 2026-09-09
GoKawiil