Briefing 2026-09-09 — ALLM Academy

01

Google: Attackers are using prompt injection against coding agents

Why it matters. Relevant to Loop Engineering. Matched Loop Engineering on: agent, coding agent. Read it through that lens.

02

Why it matters. Relevant to Loop Engineering. Matched Loop Engineering on: agent, coding agent. Read it through that lens.

03

Why it matters. Relevant to State, Memory & Durability. Matched State, Memory & Durability on: agent memory. Read it through that lens.

04

A Look at Recurrent Depth, Hidden Chains of Thought, and Recent Research on Looping Transformer Blocks
Open the source to inspect the project and its documentation.

Why it matters. Relevant to Prompt Engineering. No strong keyword match; defaulted to prompt engineering. Read it through that lens.

05

I have been a dwarfstar fan for awhile and I really liked glm 5.3 flash but needed it to be materially faster to feel good using it.
In the screenshot you can see the outcome of using the model with a claude code harness at ~200k depth, with many tool calls and averaging over 38tps output.
Yes, I put 60tps in the headline and you will get that if you ask it to write SQL.

Why it matters. Relevant to Loop Engineering. Matched Loop Engineering on: claude code. Read it through that lens.

06

Who is the marketing genius at LM Studio that decided that going ALL IN on pushing their new Bionic Agent product meant they are going to make it a giant pain in the ass to find and download actual LM Studio.
This is the dumbest marketing decision I’ve ever seen.
I used to love LM Studio, it was the middle stepping stone in the logical progression of inference.

Why it matters. Relevant to Inference & Serving. Matched Inference & Serving on: vllm. Read it through that lens.