CS2680 Modern AI Systems: Agents and System Optimizations
News from the watchlist

This page collects what the sources on blogs to watch have published recently and groups them by subject rather than by publisher. It is rebuilt every hour, so a post usually appears here within an hour of going up. Nothing on this page is required reading.

Grouping by subject is the point. A reader gives you 45 separate streams and leaves you to notice that four companies wrote about the same scheduling problem this week; this page puts those four posts under one heading. Topics come from the filter terms already listed on the blogs-to-watch page, so the vocabulary is the course's.

How a post is filed. Each post is scored by keyword against every topic, using its title and its summary, and it is filed under the topic it scores highest against. A term that names a subject on its own counts for more than one that merely co-occurs with it, and a match in the title counts for three times a match in the summary. Any second topic a post also matches is shown as a label beside it. The method is keyword matching rather than a model, which makes it predictable, cheap, and occasionally wrong.

The page shows the last 30 days, which is 488 posts of the 711 the index holds. Each topic lists its 25 most recent posts and links to the rest. Widen the window with 90 days or 120 days, which is as far back as the index goes.

Agents

Agent harnesses and orchestration

How an agent loop is built, driven, and kept on task.

67 further posts in this topic are not shown. Open the topic on its own to read them.

Coding agents

Agents that read, write, and review code, and the benchmarks that grade them.

Tools, MCP, and context

Tool interfaces, protocols, memory, and what the model is given to work with.

7 further posts in this topic are not shown. Open the topic on its own to read them.

Sandboxing and agent security

Containment, permissions, and the attacks that target agents.

Evaluation and reliability

Measuring whether an agent works, and keeping it working.

AI systems

Inference and serving

Serving engines, request paths, and end-to-end latency and throughput.

4 further posts in this topic are not shown. Open the topic on its own to read them.

KV cache and prefix caching

Reusing computed attention state across requests and turns.

Scheduling, batching, and disaggregation

How requests are batched, placed, and split across a fleet.

Model architecture and decoding

The shapes of the models being served and how tokens come out of them.

Kernels and quantization

The arithmetic itself: kernels, numerics, and compilers.

Accelerators and networking

Silicon, interconnect, and the fabric between them.

Training and RL infrastructure

The other half of the fleet: pre-training, post-training, and RL loops.

Cost, energy, and capacity

What the fleet costs to buy, run, and power.

General systems

Storage and databases

Durability, query execution, and the layers under both.

Distributed systems and networking

Agreement, addressing, and moving bytes between machines.

Serverless, containers, and virtualization

The unit of deployment and the machinery that starts it.

Observability and failure recovery

Seeing what the system did, and what happens after it breaks.

Everything else

Everything else

Posts from the watchlist that no topic above claims.

135 further posts in this topic are not shown. Open the topic on its own to read them.

Sources and the last run

The index covers 45 sources from the watchlist. 37 publish a feed and are read from it; the other 8 publish none, so their index pages are scraped and each new post's own page supplies the title and date its card omits.

Last run finished 27 Aug 2026 at 23:08 UTC. The index holds 711 posts, keeps them for 120 days, and shows 488 posts on this page.

1 source failed on the last run. Replit (HTTP 403)

The last run read 843 posts across every source and added 711 posts.

4 sources on the watchlist are not aggregated here, so check them by hand.

  • Intel Developer. The Lithium community platform answers 403 to every automated request, feed paths included.
  • Uber Engineering. The index renders client-side, there is no feed, and the only sitemap is the whole-site marketing index.
  • LinkedIn Engineering. The index renders client-side and there is no feed.
  • Artificial Analysis. A standing benchmark dashboard rather than a blog, so it publishes no post stream.

A date shown as "first seen" is not a publication date. Some sources publish no date at all, so the page records when the post entered the index instead of guessing.