I’ve been able to so far bump the context window to 75% of max but ill probably run into the same issue and will want to check out stuff like this arxiv.org/abs/2606.06492
Who's Who of AI
Vicki Boykis
Machine learning engineer, recommender systems and infra
Why they matter
Machine learning engineer, recommender systems and infra with public evidence across AI research, AI business.
- AI signals
- 0 past 30d
- Sources
- 0 distinct domains
- Discussions
- 1 past 30d
- Latest signal
- —
Founding list[float] engineer. Recsys. Personalization. Infra. Systems. Normcore code. Nutella. Vectors. Words. Vibes. Bad puns (soon).
https://vickiboykis.com/what_are_embeddings/
What they're sharing
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution arxiv.org
Running local models is good now vickiboykis.com
Tagging my blog posts with BERTopic and LLMs vickiboykis.com
Using ExceptionGroup at Anthropic (experience report) discuss.python.org
Articles & links
new post: how I develop recently using local models. the tooling is now good enough to do agentic workflows and everyone should give them a try! vickiboykis.com/2026/06/15/r...
New post: Tagging my blog with BERTopic and LLMs. I suspect as token costs increase, we'll see more blended traditional ML/LLM systems. And, in general, they work really well! vickiboykis.com/2026/05/18/t...
like, discuss.python.org/t/using-exce...
Their own posts
Recent commentary
Something happens to my brain after agentic coding that I can’t describe. It’s like cognitive offloading which folks have already written about, but even more. It feels like I can’t think through problems anymore. Like a fog. Using agentic but losing my hard-won agency.
the actual most revolutionary thing the ai labs have actually done is make it look like it's insanely easy to duct tape together python microservices with all their concurrency issues and trained models with all their transformers issues and have them run as one api call
Curious about people’s ML dependency management strategies in the face of supply chain risks. Often pinning dependencies particularly in the torch/HuggingFace ecosystem is the only way to create reproducible training and inference code but that means dependabot isn’t happy.
Their network
In Vicki Boykis's orbit
Center = Vicki Boykis. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.