Fine-tune on Muse Spark Open outputs and you owe Meta a credit line
Muse Spark Open went up on Hugging Face on 15 October under an MIT-style licence with three strings: a Built with credit that follows models trained on its outputs, a ...
Tag: news
Nemotron 3.5 Bolt says 24GB on the label and 28GB in the recipe
NVIDIA released Nemotron 3.5 Bolt 74B-A9B on 15 October. The files the recipe loads total 24.75 GB, there is no 24 GB discrete recipe, and the PinchBench #1 claim trails ...
Claude API traces won’t reach a collector on 4318 or a private IP
Anthropic shipped OpenTelemetry trace export for the Claude API on 14 October. We read the delivery rules: port 443 only, public hostnames only, redirects disable the destination, and spans aren't ...
Meta’s API sells Muse Wonder, not the Wonder Full that tops its chart
Meta launched Muse Wonder and Muse Wonder Full on 12 October. We read the model card and the price page: the API gets the weaker one, and the benchmark footnotes ...
LFM2.5-24B-A2B beats Qwen3.6 at tools and loses SWE-Bench by 15 points
Liquid AI released LFM2.5-24B-A2B with open weights. We read the full benchmark table and the license: strong at tool calls, weak at coding, and not free for every company.
Requests to gemini-3.7-flash now get 3.8 Flash, with no shutdown date
Google deprecated Gemini 3.7 Flash on 8 October and routes its traffic to 3.8 Flash, a month after calling 3.7 the efficiency pick. Here's what moves on the bill and ...
OpenAI’s Decisions API charges $0.10 in and nothing out, with no cache
Decisions returns a probability, a choice or a score instead of text, on gpt-6-luna only. It's $0.10 in and free out, but with no caching a long rubric can cost ...
GPT-6.1 Sol Ultrafast bills six times Sol and 1.2 times Astra
Ultrafast on GPT-6.1 Sol costs $12 and $60 per million tokens: six times standard Sol, three times Fast, and 1.2 times Astra at normal speed. The guide is silent on ...
Claude Haiku 5.5 is $0.10 per million until a prompt passes 100K
Anthropic released Claude Haiku 5.5 on 7 October at $0.10 and $0.50 per million tokens. The footnote matters more than the headline: past 100,000 prompt tokens the rate jumps fivefold.
Reflection Beam is a 501B open model with no weights yet
Reflection AI's Beam is a 501B mixture of experts with an Apache 2.0 promise, a waitlist and benchmark scores nobody outside can check yet.