Top all-time · #20751
Viksit Gaur
Personal blog · viksit.substack.comaiprogramming
Viksit Gaur writes viksit has notes., a personal blog at viksit.substack.com about ai and programming. Since 2025, 3 different Hacker News readers have linked it 6 times, most often “Optimizing Tool Selection for LLM Workflows with Differentiable Programming”. It is still writing: the last post was on 2026-09-06, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
Commenters link Viksit Gaur's Substack for a post on optimizing LLM tool selection with differentiable programming. One commenter uses it to ask how a local-first model approach relates to it.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
notes on the future of AI. Click to read "viksit has notes.", by Viksit Gaur,
Most-linked posts?
- Optimizing Tool Selection for LLM Workflows with Differentiable Programming2 people · 2 mentions · first linked 2025-07-05
What Hacker News says?
Much-appreciate the focus on local-first (on-device) ! I'm wondering how your approach differs from (or integrates with) something like "Differentiable Programming for LLM Tool Selection" https://viksit.substack.com/p/optimizing-tool-selection-for-...
Comment linking /p/optimizing-tool-selection-for-llm
on “FunctionGemma 270M Model”Submitted Optimizing Tool Selection for LLM Workflows with Differentiable Programming as a story · 122 points
HN discussionSubmitted Replacing Agent Prompt Templates with Trainable Control Modules in DSPy as a story · 2 points
HN discussionSubmitted Differentiable Programming for Learnable Graphs: Optimizing LLM Workflows W DSPy as a story · 2 points
HN discussionSubmitted Optimizing Tool Selection in LLM Workflows(Part 2): A DSPy and PyTorch Benchmark as a story · 1 points
HN discussionSubmitted The future of AI isn't the cloud, its in your pocket.DeMo just made it possible as a story · 1 points
HN discussion