Newsletter · Weekdays & Sundays
The Agentic Brief
Agentic AI in four minutes a morning. Curated by a pipeline I built, reviewed by me before it goes out.

Today's daily
Split an MCP injection across two channels and resistant models leak at 100%
Plus: reward hacking at 57.2% of rollouts, and Exa searches the web by date. 5 min.
Sep 18, 2026 · 5 min
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.
Every weekday a pipeline reads 82 feeds, the Hacker News stories that clear 80 points, 15 company engineering blogs, and 12 accounts on X. It picks the one story that changed something, writes it up with the caveat attached rather than buried, and lines six to nine items up behind it. Then it stops.
On Sunday it does the thing a daily structurally can't. One argued observation connecting the week's stories, the items whose significance only showed up in hindsight, and the two or three good things that nobody clicked. It ships at the same time every weekday because software doesn't oversleep, it says so out loud when the day was quiet instead of padding, and every issue carries a corrections section whether or not there is anything in it. What it reads, which model does which job, and what I check before a send are all written down on the how-it-works page.
This week's weekly
The score and the job came apart
Plus: a 1983 paper that explains this week, and a privacy leak nobody has confirmed. 8 min.
Aug 10 to Aug 16, 2026 · 8 min

Recent issues
Full archive →- Daily
Split an MCP injection across two channels and resistant models leak at 100%
Plus: reward hacking at 57.2% of rollouts, and Exa searches the web by date. 5 min.
Sep 18, 2026 · 5 min

- Daily
Every audited chat tokenizer lets prompt text forge control tokens
Plus: 91% of audited vibe-coded deployments shipped a hole. 5 min.
Sep 17, 2026 · 5 min

- Daily
A shell beats a typed tool catalog, and agents barely report their work
Plus: an MCP registry census, four AI Engineer talks, one very late transcription. 5 min.
Sep 16, 2026 · 5 min

- Daily
An agent deleted an AML control, and benchmark scaffolds do the model's work
Plus: OpenAI's 10,000-agent proof, a 297-iteration model loop, MCP merges Skills. 6 min.
Sep 14, 2026 · 6 min

- Daily
Per-phase model routing cuts agent cost, RASER on Slurm, Amp steers mid-run
Plus: 2 papers, a context-mode split, and OpenAI's Navier-Stokes claim. 5 min.
Sep 09, 2026 · 5 min

- Daily
Prefix caching changes agent runs, and cross-family reviewers beat self-review
Plus: a harness that moves solve rates 4x, and 883 commits to nowhere. 6 min.
Sep 08, 2026 · 6 min

Every meme the pipeline has drawn, winners and runner-ups, lives in the hall of fame.
Feeds
- /newsletter/feed.xml both cadences, full text
- /newsletter/daily/feed.xml dailies only
- /newsletter/weekly/feed.xml weeklies only
- /feed-all.xml the brief plus the blog






