Frontier Daily (Nov 10): 6 items from Hacker News, Simon Willison, Latent Space
A Hacker News post with 65 upvotes and 10 comments shares an LLM inference learning resource consisting of 6 hours of YouTube content and 85…
Every day Laojin pulls the official channels and compiles the past 48 hours of AI news into a short brief: curation only, no commentary, with the original link and publish time attached to every item.
1. 6 Hours of YouTube and 85 handtyped pages of notes on LLM Inference – Start here
A Hacker News post with 65 upvotes and 10 comments shares an LLM inference learning resource consisting of 6 hours of YouTube content and 85 hand-typed pages of notes as a starting point.
Source: Hacker News · 2026-11-09 · Original
2. ChatGPT Desktop forwards your SSH agent to remote machines
A Hacker News post with 139 upvotes and 46 comments reports that ChatGPT Desktop forwards the local SSH agent to remote machines, letting an agent on the remote machine authenticate with local SSH credentials, such as pushing to private GitHub repos, with a linked openai/codex PR discussion as proof.
Source: Hacker News · 2026-11-09 · Original
3. The Web Is More Than Enough, by Paul Ford
Simon Willison shares his Hacker News comment on Paul Ford's "The Web Is More Than Enough" and shows a nudibranch-themed Faberge egg he built in Three.js, plus a version Claude Opus 5.5 ported to vanilla JS + WebGL in the same thread, noting the two are not identical and linking the Claude transcript.
Source: Simon Willison's Weblog · 2026-11-09 · Original
4. Hide your slop PR descriptions behind
Simon Willison notes that PRs for his projects now mostly come from Claude Code or Codex, and that agent-written PR descriptions, though accurate and comprehensive, read like slop due to their length; he proposes hiding most of the text inside an HTML details/summary element and keeping a short human-judged introduction.
Source: Simon Willison's Weblog · 2026-11-09 · Original
5. How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco
Latent Space interviews Mihail Eric, who teaches The Modern Software Developer at Stanford and leads AI at Monaco, about the CS146S syllabus and which lessons held up with his own engineering team, noting that the second run brought open-source maintainers into the course so students learn an unfamiliar repo, propose a change, and explain the patch to the person who might merge it.
Source: Latent Space · 2026-11-08 · Original
6. [One Million AI Engineer Special] How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco
undefined
Source: Latent Space · 2026-11-08 · Original
---
_Sources: official blogs of OpenAI, Google DeepMind and Qwen; official RSS of Simon Willison, Latent Space, Import AI and One Useful Thing; Anthropic site monitoring, top AI discussions on Hacker News and open-source updates from key AI orgs on GitHub. Mistral / Meta AI have no stable public feed; X sources are curated by hand. This is a source digest — no commentary from Laojin._
Made by Laojin · AI that ships
365SkillAn agent-skills lab: 14 in-house skills
365Skill is our public lab for agent skills: a standard SKILL.md format, a deny-by-default publish policy, and an evals harness. It holds 14 original 365 skills — 12 public and 2 internal. Apache-2.0 — star it, install it, file issues.
More from Laojin: Sellenca · 365AIOrg · AllModelsAPI · 365Loopa · 365 Ops
Related
Linked by topic, people and hubs