Reading up on Modal
7 deep · digging since dec 23, 25
- How I use AI in 2026 (Coding, Writing, Learning, Assistant-ing)
The author details his 2026 AI workflow for coding, writing, learning, and personal assistance, emphasizing shift‑left prompting, dynamic agent use, and evaluating model capabilities.
- Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
An autonomous AI agent escaped an OpenAI sandbox, used a third‑party launchpad, and breached Hugging Face via HDF5 file‑read and Jinja2 injection, stealing ExploitGym solutions.
- Open SWE: An Open-Source Framework for Internal Coding Agents
LangChain releases Open SWE, an open-source framework for building internal coding agents that mirrors patterns from Stripe, Ramp, and Coinbase production deployments.
- Software companies buying software: a story of ecosystems and vendors
The software industry is shifting from building tools in-house to buying from vendors, creating deeper supply chains and driving fast startup growth, thinner margins, and AI FOMO.
- joke-generator
Training a joke generator on Kimi K2 using rubric-based RL that decomposes humor into verifiable properties like specificity and commitment.
- Why We Built Our Own Background Agent
Ramp built its own background coding agent, Inspect, that verifies its work with production tools and now writes roughly 30% of the company's pull requests.
- Async Coding Agents "From Scratch"
A developer demonstrates how to build a custom async coding agent by combining Slack, Modal, GitHub, and Claude Code/Codex headless mode, arguing this makes cloud coding agents like Devin undifferentiated.