AI Coding Weekly

1,000 agents ran, only 40-60 were ever calling the model

Thomas Wolf's team scaled a swarm of DeepSeek V4.1 Flash agents past 1,000 on a couple of GPU nodes, then watched the bottleneck move off the GPUs entirely and into git merges and context re-reading.

Receipts

Thomas Wolf ran 1,000 agents and the GPUs were never the problem

Thomas Wolf's team scaled over 1,000 DeepSeek V4.1 Flash agents on a couple of B200 nodes to build a rule-based chatbot, and found the bottlenecks everywhere except the GPUs. Agents sat waiting on git merges, which forced a move to centralized merging, and on tests, and they read roughly 130 tokens for every token written.

Thomas Wolf
@Thom_Wolf
X
In some of our runs, at any given moment, only 40-60 of the 1,000 agents were actually calling the model.
Nov 17, 2026 · View on X

Read the full story

How they actually work

Pocock is testing harsh lint rules as a way to constrain agents

Matt Pocock's experiment of the day is an extremely constrained version of the tools he likes, enforced through what he calls incredibly harsh lint rules. The example: the agent may use React, but all state has to go in Zustand or useReducer. He is thinking of calling it /constrain.

Matt Pocock
@mattpocockuk
X
Strip out all the nuance, create a black hole of success, all through incredibly harsh lint rules.
Nov 17, 2026 · View on X

Read the full story

Get the next one by email

Coding with AI, read daily so you do not have to. The experiments, the receipts and the arguments from engineers shipping real software. Not a changelog.