Freek Van der HertenAug 11, 20261 min readintro

Amped up

Summary

The post highlights Sebastian’s shift to using Amp as his primary AI coding harness, emphasizing improved user experience over model churn, and mentions AGENTS.md tweaks that cut down unnecessary verification during everyday coding.

Amp is now the author’s default AI coding harness because its UX feels smoother than chasing model updates.
Adjustments in AGENTS.md reduce over‑eager verification steps, making day‑to‑day coding faster.
The summary links to the original write‑up but provides no implementation specifics.

Engineers evaluating AI coding assistants should note that UX and verification noise can impact productivity more than raw model performance.

3/10

ai productivity php coding assistants

Related reading

An Empirical Study of Harness Design for Coding Agents arxiv.org
This empirical study dissects coding agent harness components like planning, action space, and context management. It finds context management is critical for tight windows, rule-based elision is efficient, and planning shifts from accuracy to cost savings for stronger models.
Hugging Face Daily Papersarxiv.orgRun-Ze Fan, Zihao Zhang, Simin Ma5d2 minpaperHN12621
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement arxiv.org
ModularRSI proposes a contrastive, modular approach to evolve agent harnesses by independently updating five functional modules and aggregating evidence across 2,000 benchmark‑disjoint tasks. Experiments on TB2.0 and SWE‑Bench Verified show consistent gains on unseen tasks and cross‑model transfer.
Hugging Face Daily Papersarxiv.orgSiwei Wu, Jincheng Ren, Yizhi Li8d1 minpaper
Maintaining the love for coding in the time of AI nlnetlabs.nl
Lobstersnlnetlabs.nl6dHN21 lobste.rs32
From Individual Experiments to a Shared AI Practice: How Avant Scaled AI-Assisted Engineering qubika.com
Avant replaced many personal AI‑assistant setups with a single, organization‑wide Claude Code configuration that embeds the company’s coding standards, project‑tracking links, and documentation. Treated as an internal product, the setup is versioned, owned by delivery engineers, and iteratively improved. The shared tool speeds routine tasks (scaffolding, tests, migrations, docs) and enforces cons…
Moove-itqubika.comFernanda Mezquita4d2 min
Show HN: Share your AI Setup, Learn from others mysetup.ai
A Show HN post announcing mysetup.ai, a community‑focused site where users can list the LLM tools, agents, and workflows they use. The author shares a few example profiles and invites others to add theirs, but provides no technical details, design rationale, or measurable insights.
Hacker News front pagemysetup.ai5d1 minHN244138
Towards Self-Driving Codebases detail.dev
The post argues that AI agents could eventually handle low‑level engineering tasks—bug fixing, debugging, UI consistency, growth experiments—if the dev toolchain is made “agent‑legible”. It outlines missing primitives (global memory, code‑base rot prevention, better dev environments) and proposes a bootstrapping process to measure and improve a repo’s “agent readiness”. The piece is largely specu…
Hacker News front pagedetail.dev4d9 minHN12099

Amped up

Summary

Related reading

An Empirical Study of Harness Design for Coding Agentsarxiv.org

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvementarxiv.org

Maintaining the love for coding in the time of AInlnetlabs.nl

From Individual Experiments to a Shared AI Practice: How Avant Scaled AI-Assisted Engineeringqubika.com

Show HN: Share your AI Setup, Learn from othersmysetup.ai

Towards Self-Driving Codebasesdetail.dev

An Empirical Study of Harness Design for Coding Agents arxiv.org

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement arxiv.org

Maintaining the love for coding in the time of AI nlnetlabs.nl

From Individual Experiments to a Shared AI Practice: How Avant Scaled AI-Assisted Engineering qubika.com

Show HN: Share your AI Setup, Learn from others mysetup.ai

Towards Self-Driving Codebases detail.dev