Siobhan Rossi
@shivros.bsky.social
Applied AI Engineer · RAG, Retrieval Evaluation, Prompt & Cost Optimization, Data-Centric Systems
OpenRouter has the rare "Wrapped" that didn’t make me roll my eyes too hard.
Personal usage only. No work or vibe coding included:
* 256.1M tokens routed
* 77 models used
Overdone trend, but this one made me grin a bit.
Embarrassed a grok model made it into my top 5.
Personal usage only. No work or vibe coding included:
* 256.1M tokens routed
* 77 models used
Overdone trend, but this one made me grin a bit.
Embarrassed a grok model made it into my top 5.
December 18, 2025 at 9:15 PM
OpenRouter has the rare "Wrapped" that didn’t make me roll my eyes too hard.
Personal usage only. No work or vibe coding included:
* 256.1M tokens routed
* 77 models used
Overdone trend, but this one made me grin a bit.
Embarrassed a grok model made it into my top 5.
Personal usage only. No work or vibe coding included:
* 256.1M tokens routed
* 77 models used
Overdone trend, but this one made me grin a bit.
Embarrassed a grok model made it into my top 5.
MIT’s VideoCAD (zurl.co/YwfkN ) AI learned CAD by watching 41k+ videos of humans clicking, dragging, and typing.
Super cool, but positively unhinged. Why are we automating UI use?
Super cool, but positively unhinged. Why are we automating UI use?
December 16, 2025 at 10:49 PM
MIT’s VideoCAD (zurl.co/YwfkN ) AI learned CAD by watching 41k+ videos of humans clicking, dragging, and typing.
Super cool, but positively unhinged. Why are we automating UI use?
Super cool, but positively unhinged. Why are we automating UI use?
Checked out "AI's 70% Problem w/ Addy Osmani" (zurl.co/pyG2O) — an episode of Zed Industries' podcast. The TL;DR: AI can write about 70% of the code you need, while the remaining 30% demands nuance the models simply don’t have.
November 26, 2025 at 1:30 AM
Checked out "AI's 70% Problem w/ Addy Osmani" (zurl.co/pyG2O) — an episode of Zed Industries' podcast. The TL;DR: AI can write about 70% of the code you need, while the remaining 30% demands nuance the models simply don’t have.
Stanford built a model (Evo 1.5) that works like an LLM, except it runs on bacterial DNA instead of text tokens. You give it some genomic context, and it can complete genes or even invent new ones.
November 26, 2025 at 12:00 AM
Stanford built a model (Evo 1.5) that works like an LLM, except it runs on bacterial DNA instead of text tokens. You give it some genomic context, and it can complete genes or even invent new ones.
Codex CLI down. Back to Stack Overflow copy-pasting like it's 2019.
November 22, 2025 at 9:23 PM
Codex CLI down. Back to Stack Overflow copy-pasting like it's 2019.