Entity trail

Dan McAteer

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-06 / sources-researcherLatent Space on five days with Grok Bot: the Bot, not the config file, becomes the unit of programmingDan McAteer's 2026-09-05 piece argues Grok Bot matches OpenClaw's power but at a different level of abstraction — plugins connect by browser login rather than MCP server JSON and pasted API credentials, and he wired up an X-based daily brief and a Freshdesk ticket bot on a fifteen-minute poll with no code. His framing: Grok Bot is a managed agent computer, OpenClaw is a user-owned agent platform, and OpenClaw 2.0 narrowed the setup gap but not that distinction. He also installed the Claude Code CLI inside Grok Bot's virtual computer, pointing at a council-of-agents pattern.
2026-08-23 / sources-researcherLatent Space: The Agent Harness Is Being Absorbed Into the Weights, and What's Left Will Be a Harness for Human AttentionDan McAteer's August 22 Latent Space essay argues the Christmas 2025 jump in agent usefulness was not a model event or a harness event but the two improvement curves crossing. He traces four stages: ReAct as the loop on paper (Oct 2022), AutoGPT and BabyAGI as premature autonomy where the harness ran ahead of model capability, Cursor and Copilot pulling the harness back below the model curve with a human in the loop, and the current phase where models absorb harness scaffolding into post-training and engineers delete what got absorbed. The concrete number worth keeping: 95% per-step reliability across a 20-step task compounds to roughly 36% success, which is why a loop below a capability threshold amplifies errors instead of results. He quotes Lukasz Kaiser saying the winter change was hard to attribute to any single component.
2026-08-22 / rss-researcherHarness-Bench shows a 23.8-point spread on identical model weights, and Anthropic deleted 80% of Claude Code's system prompt without losing capabilityDan McAteer's Latent Space essay traces the agent harness through four phases from ReAct (Oct 2022) to Claude Code (Feb 2025, ~$1B ARR in six months), and cites Harness-Bench scoring the same model between 52.4 and 76.2 depending only on the harness around it. OpenAI tripled GPT-5.6 Sol's ARC-AGI-3 score from 13.3% to 38.3% through harness changes alone, while Anthropic recently removed 80% of Claude Code's system prompt with no capability loss. The argument for builders: harness capability is being absorbed into weights via RL, so what remains is an interface for managing scarce human attention, not for managing the model.

Graph relationships

USES
Grok Bot
Dan McAteer used Grok Bot to build agent automations without code on a fifteen-minute poll.
Source finding
USES
OpenClaw
Dan McAteer compared OpenClaw with Grok Bot for agent platform capabilities.
Source finding

Source trail

Latent Space Latent Space

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…