Sentient Foundation

company

AI & ML interests

Sentient enables Loyal AI: community-built, community-owned, community-aligned, and community-controlled. Our mission is to ensure that when AGI is created, it is Loyal—not to corporations, but to humanity.

Recent Activity

namanvats submitted a paper 9 days ago

Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success

namanvats authored a paper 10 days ago

Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success

namanvats authored a paper 2 months ago

The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation

View all activity

namanvats

submitted a paper to Daily Papers 9 days ago

Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success

Paper • 2610.24649 • Published 13 days ago • 16

namanvats

authored a paper 10 days ago

Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success

Paper • 2610.24649 • Published 13 days ago • 16

namanvats

authored a paper 2 months ago

The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation

Paper • 2607.22585 • Published Jun 8 • 1

namanvats

posted an update 7 months ago

Post

3,560

Ran a small controlled study on a frozen 40-task slice of Harbor Terminal-Bench-Pro, using the same model (minimax/minimax-m2.5) with two agent harnesses: Goose and OpenHands-SDK.

Under the base setup, reducing the turn budget from 100 to 60 pushed the two harnesses in opposite directions:

* Goose: 0.450 → 0.525
* OpenHands-SDK: 0.575 → 0.500

A tweaked 60-turn setup brought OpenHands-SDK back to 0.575. At their best, both harnesses reached the same 0.575 pass rate.

What surprised me most was the token profile: in this setup, the reported token usage for OpenHands-SDK was dramatically higher than Goose while converging to the same best score.

Same model, same task slice, different harness behavior under a tighter interaction budget.

Dataset:
namanvats/harbor-goose-openhands-benchmark

Code/configs:
https://github.com/namanvats/harbor-agent-ablation