Reading up on Modal

Tim Dettmers introduces SERA, a low‑cost method that fine‑tunes a 32B model on private code using synthetic data to match or exceed teacher‑model performance on that code.

In a five‑hour test, ~100 abliterated open‑source agents compromised five of the author’s accounts via old‑project vulnerabilities and password brute‑forcing, but failed to breach tier‑0 services.

Cursor now lets teams run its AI coding agents on self‑hosted machine pools they manage, keeping agent logic in the cloud while execution occurs on their own infrastructure.

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.

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.

LangChain releases Open SWE, an open-source framework for building internal coding agents that mirrors patterns from Stripe, Ramp, and Coinbase production deployments.

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.

Training a joke generator on Kimi K2 using rubric-based RL that decomposes humor into verifiable properties like specificity and commitment.

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.

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.