Open Source Factory

Pace the Frontier: AI's Rivals Agree They Should Slow Down by OpenSource Factory · September 14, 2026 I stopped halfway through Dario Amodei's new essay on Saturday morning. The CEO of Anthropic was writing — plainly, no hedging — that the industry should deliberately slow down how fast it makes its models smarter. Not “invest more in safety,” which everyone in this business says. Not “the other labs should be careful.” Slow down. Then I scrolled a little further and found Sam Altman and Elon Musk saying the same thing over the same weekend. That does not happen. The line that made me stop was about distance, not philosophy: “Given the accelerating rate of AI capability development, it's my worry that in 6–12 months such a swarm could be capable of taking over the entire internet with a persistent botnet (potentially causing hundreds of billions of dollars in damage).” That's 6–12 months, written by the perso...

DeepSeek V4.1 Flash: 748B Parameters, 8B Active, 70% Cheaper by OpenSource Factory · September 11, 2026 A couple of days ago I wrote a post about a model whose own name was a deadline. deepseek-v4.1-flash-expires-on-0910 — DeepSeek had dropped an intermediate build into the live API and given it two days to live. That post ended with a promise: if the official numbers held up, I would follow the release the same week. It landed on September 10, on schedule, and it came with something I did not expect in the same announcement: DeepSeek is switching off V4-Pro. The flagship model is being retired in an orderly manner, in DeepSeek's own words, and from September 14 every request aimed at deepseek-v4-pro gets routed to the cheap Flash model instead. That arrangement stays in place until V4.1-Pro shows up. The company that spent August raising its prices just cut them, and the model it is cutting them for is the one it is now using to replace its own flagship. So what a...

Images 2.5: $527 vs $2,110 for 10,000 Images September 9, 2026 · by opensourcefactory1 · all model claims below are vendor-reported unless stated otherwise I opened OpenAI's Images 2.5 announcement expecting the usual sharper-faster-better bingo card. Then I hit the pricing calculator and stopped scrolling, because the same "high" quality setting now costs roughly a quarter of what it did last week. Same pixels, new labels. That pricing twist turned out to be the most concrete thing in the whole launch. I cover open image and video models on this blog, and this one is closed weights, so why write about it? Because the pricing relabel is a genuinely consumer-friendly move wrapped in confusing labels, and because Sketch, the doodle-to-image feature, is the first ChatGPT image tool in a while that made me want to try it myself. Short version up front: the model looks like a solid step forward, the tools are the fun part, and the price story needs a decoder ring, which i...

DeepSeek V4.1 Flash: a 507 tok/s Beta That Expires September 10 by OpenSource Factory · September 9, 2026 A model ID with an expiry date baked right into it — deepseek-v4.1-flash-expires-on-0910 . I saw that string yesterday morning and laughed out loud, then immediately opened the API docs to check whether it was real. It is. DeepSeek dropped an intermediate V4.1 Flash build into the live API on September 8, gave it roughly two days to live, and attached a feedback form asking testers one remarkable question: can this thing replace V4 Pro? So here is the short version up front. This is not a launch — no model card, no technical report, no changelog entry, no published specs at all. It is a two-day public test of a checkpoint DeepSeek itself calls an intermediate version, billed at exactly the same rates as V4 Flash, capped at 20 concurrent requests per account, and scheduled to vanish around September 10. The community numbers flying around are genuinely eye-cat...

Sol-H3: 5 Seconds of Video in 1.65 Seconds Sept 7, 2026 · by OpenSource Factory · AI Video · 7-min read  |  All figures vendor-reported unless marked independent; prices checked Sept 7, 2026 NVIDIA's Enze Xie posted two numbers that stopped my scroll: five seconds of world, 1.653 seconds to infer. The release is Sol-H3, NVIDIA Research's fastest end-to-end MiniMax-H3 inference stack, and it generates video faster than you watch it. On a single 8-GPU B300 system, a 5-second 1344x768 clip with stereo audio renders in 1.653 seconds. That is roughly 3x realtime, and it is the moment video generation crosses from fast rendering into streaming territory. One paragraph of context before the numbers. Sol-H3 is not a new model. It is NVIDIA's Sol-Engine and Sol-Attn runtime wrapped around MiniMax's open-weight H3, running a 4-step profile instead of the 50-step base. The weights are still MiniMax's under their community license; the stack code is Apache 2.0. An...

Astra vs Fable 5.1: Same $10/$50, Different Bills Sept 5, 2026 · by OpenSource Factory · Frontier matchup · 8-min read  |  All benchmarks vendor-reported unless marked independent; prices checked Sept 5, 2026 Two frontier models shipped 48 hours apart with the exact same price tag, and neither company benchmarked against the other. OpenAI's GPT-6 Astra landed September 3 calling itself the AGI era; Anthropic's Claude Fable 5.1 landed September 1 with a quiet cache-price cut doing the loud work. I have covered both launches separately on this blog, and the comparison is the post I kept getting asked for, so here it is, with both sides getting their real wins. The one-paragraph version: Astra takes most of the shared benchmark rows, usually by real but thin margins, and owns computer use, math, and cyber outright. Fable 5.1 takes broad reasoning decisively, holds both independent Artificial Analysis crowns, and wins the rate card on big requests. Then th...

AMD Halo Station: 96 Cores, 576GB, a Trillion Parameters Sept 5, 2026 · by OpenSource Factory · Local AI · Hardware · 7-min read  |  All specs vendor-reported unless marked estimate I opened the IFA keynote recap expecting another mini-PC refresh. Then Jack Huynh rolled out a liquid-cooled tower with Instinct accelerators inside it and I actually sat up. AMD is calling it the Threadripper Halo Station, and the pitch is simple: datacenter-class memory on your desk, no cloud queue, no shared tenancy. So here is the short answer up front. This is AMD's DGX Station rival: a 96-core Threadripper PRO plus up to four Instinct MI350P cards, up to 2.6TB of combined memory and up to 16.4TB/s of total bandwidth, aiming at trillion-parameter models run locally. It is a prototype, it ships through OEM partners sometime in 2027, and there is no official price or date yet. Everything below carries that prototype caveat, and I will redo this post the moment rea...