VQV Signal

DEVELOPING WATCH TECHNICAL

Joscha Bach calls AI agents negotiating code in human language 'absolutely ridiculous'

According to a post on X by @Plinz, Joscha Bach argues it is "absolutely ridiculous" in 2026 that AI agents still talk to each other in human language about how to write code in programming languages built for humans. The post is a short statement of opinion, and the source does not describe a specific proposal, experiment or alternative protocol. The item appears in the Scobleizer News Pulse feed, which describes Bach as a prominent AI thinker pressing the industry on agent-to-agent protocols beyond natural language.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-06T06:41:00+00:00 Detected 2026-11-06T22:17:26+00:00
View original source

According to a post on X by @Plinz, Joscha Bach argues it is "absolutely ridiculous" in 2026 that AI agents still talk to each other in human language about how to write code in programming languages built for humans. The post is a short statement of opinion, and the source does not describe a specific proposal, experiment or alternative protocol. The item appears in the Scobleizer News Pulse feed, which describes Bach as a prominent AI thinker pressing the industry on agent-to-agent protocols beyond natural language.

AI-assisted summary based on the listed source.

Joscha Bach argues it is “absolutely ridiculous” in 2026 that AI agents still talk to each other in human language about how to write code in programming languages built for humans. Why it matters: A prominent AI thinker is pressing the industry on agent-to-agent protocols beyond natural language. Original post on X

Developers and companies building multi-agent systems may want to track whether agent-to-agent communication moves beyond natural language toward formats designed for machines. The source gives no concrete design, timeline or named alternative, so any practical change is not yet clear. Watch for specific protocols or follow-up statements from Bach or other agent builders.

Signal Strength 86% Technical label WATCH Public Interest 22 Category DEVELOPING Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 0 Novelty Interest Score 70 Consequence Score 18 Curiosity Score 16 Shareability Score 41

VQV surfaced this signal because it is recent, relevant to AI Agents, connected to Scobleizer News Pulse (X).