55 stories
What happens to System One decision models outside English: a position prior in Laya, an open Japanese model, a translated benchmark, and what transfers back to English. Decision models had a big September. TypeSafe AI shipped Jev and called it the first "System One" model.
Checking in on Opus 5.5 ~1 week after launch. It's the #1 model in share of spend and share of tokens among Anthropic models on OpenRouter Switching from Opus 5 has been particularly rapid
Gemma 4 vs Qwen 3.5 at every size, 0.8B to 397B, plus where Qwen 3.6 and 3.8 27B fit. Benchmarks, VRAM needs, and the right pairing for your hardware.
Ollama now supports decision models, based on TypeSafe's Jev API for fast, typed decisions. Decision models can now be run at no cost with low latency. Based on text, decision models answer yes-or-no questions, choices and scores about it, with a probability for every option.
There's no qwen3.7 on Ollama. 3.7 is API-only. Run Qwen 3.8 27B locally instead: VRAM by quant, Modelfile, num_ctx and tool calling.
To run a System One model locally, pick a runtime too: Ollaya serves ten open model families, laya-mlx runs Laya on Apple silicon, and llama.cpp needs a shim.
A quiet day lets us discuss the work behind the scenes - now open for business!
Bonsai 1.7B has been the quiet entry in PrismML's lineup since March, overshadowed by the flagship Bonsai 27B that made headlines for fitting a 27B-class model on an iPhone.
Faster inference: decode speedups up to 3.13x on device and 2.66x on an H100, with end-to-end gains up to 2.62x and 2.27x.
Jev's first week brought a trusted monitor, computer-use agents, self-hosted clones, a benchmark and a joke chatbot: the slot each fills and which numbers hold.
The open-source alternatives to Jev are Laya, Kev, SemIf, Open-Jev and Nimble. They are four kinds of project, and here is what each one replaces.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Reranking with TypeSafe Jev, move a bank anywhere with clone, export and rename, filter memories and documents by time, a separate LLM for mental-model refreshes, and many other stability fixes
Today's haul: 20 tools · 20 resources · 30 reads · 22 numbers · 35 things that happened. Every tool, resource and read below has a working link. No link, no listing.
For most of you reading, your card statement looks less like a list of hobbies and more like the most recent edition of LMArena.
Steve Yegge has been very popular and loud in his gung ho adoption of tokenmaxxing, so it is sobering to see him now shut down Gas Town and admit that despite spending many thousands a month on coding agent subscriptions… he only ever built Gas Town with it:
TL;DR Taking place October 20 to 21 in San Jose, California, PyTorch Conference North America 2026 highlights open research, tooling, and performance optimization across compiler architecture, cross-hardware kernel domain-specific languages,...
Showing 36 of 55 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
