Tag

#harness

91 posts7 followers

Explore Hashnode

Alternatives

Why Outcome-Only Evals Let Coding Agents Guess Blindly: Outcome Evals vs. a Behavioral Action-Sequence Gate (-95.2% Tokens)

💡 AI Labo Benchmark Series — Experiment E40 (Behavioral Trajectory Gates) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isolated Proxmox

6 min readtappers.hashnode.dev

tappers1d ago

Thoughtworks' Guides-and-Sensors Pattern in Action: Bare Errors vs. Feedforward Guides + Remediation Sensors (-95.1% Tokens)

💡 AI Labo Benchmark Series — Experiment E39 (Architectural Control & Guides + Sensors) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isol

7 min readtappers.hashnode.dev

tappers1d ago

Defeating Reward Hacking in Coding Agents: Prompt-Only Rules vs. a Cryptographic SHA-256 Test Lock (2.46x Faster)

💡 AI Labo Benchmark Series — Experiment E38 (Anti-Cheating & Test Integrity Locks) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isolated

7 min readtappers.hashnode.dev

tappers1d ago

Stopping Blind Micro-Retries on Identical Errors: Death-Spiral Thrashing vs. a 3-Hypothesis Pivot Ladder (-95.2% Input Tokens)

💡 AI Labo Benchmark Series — Experiment E37 (Loop Recovery & Stuck Detection) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isolated Prox

7 min readtappers.hashnode.dev

tappers1d ago

Preventing Multi-Session Amnesia in Coding Agents: Prose Summaries vs. a 3-Artifact Shift-Handover Harness (-95.2% Input Tokens)

💡 AI Labo Benchmark Series — Experiment E36 (Multi-Session Continuity & State Handover) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-iso

6 min readtappers.hashnode.dev

tappers3d ago

Why a 500-Line AGENTS.md Hurts Coding Agent Accuracy: Monolithic Encyclopedia Prompts vs. a 30-Line Directory-Pointer Index (3.13x Faster)

💡 AI Labo Benchmark Series — Experiment E35 (Context Hygiene & AGENTS.md Architecture) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isol

7 min readtappers.hashnode.dev

tappers3d ago

Eliminating Print-Debugging Loops in Coding Agents: Bare Stack Traces vs. Runtime Frame Variable-Snapshot Injection (-95.0% Input Tokens)

💡 AI Labo Benchmark Series — Experiment E34 (Runtime Introspection & Debugging Sensors) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-iso

7 min readtappers.hashnode.dev

tappers3d ago

Why Hand-Written Example Tests Fail AI Coding Agents: Fixed Sample Tests vs. a Property-Based Invariant Fuzzing Sensor (-95.1% Input Tokens)

💡 AI Labo Benchmark Series — Experiment E33 (Verification & Property Fuzzing) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isolated Prox

7 min readtappers.hashnode.dev

tappers3d ago

Why Coding Agents Need a Pre-Submit Diff Audit Gate: Blind Unchecked Submits vs. Blast-Radius & Entropy Auditing (-95.0% Input Tokens)

💡 AI Labo Benchmark Series — Experiment E32 (Verification & Pre-Submit Gates) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isolated Prox

7 min readtappers.hashnode.dev

tappers3d ago

Stop Letting Coding Agents Do Manual Multi-Spot String Replacements: Manual Text Edits vs. Parameterized AST Codemod Tools (-94.8% Input Tokens)

💡 AI Labo Benchmark Series — Experiment E31 (Edit Primitives & AST Tooling) This post is part of our empirical benchmark series testing AI coding agent harness patterns inside network-isolated Proxmo

7 min readtappers.hashnode.dev

Search Hashnode

Explore Hashnode

Trending tags this week

Why Outcome-Only Evals Let Coding Agents Guess Blindly: Outcome Evals vs. a Behavioral Action-Sequence Gate (-95.2% Tokens)

Thoughtworks' Guides-and-Sensors Pattern in Action: Bare Errors vs. Feedforward Guides + Remediation Sensors (-95.1% Tokens)

Defeating Reward Hacking in Coding Agents: Prompt-Only Rules vs. a Cryptographic SHA-256 Test Lock (2.46x Faster)

Stopping Blind Micro-Retries on Identical Errors: Death-Spiral Thrashing vs. a 3-Hypothesis Pivot Ladder (-95.2% Input Tokens)

Preventing Multi-Session Amnesia in Coding Agents: Prose Summaries vs. a 3-Artifact Shift-Handover Harness (-95.2% Input Tokens)

Why a 500-Line AGENTS.md Hurts Coding Agent Accuracy: Monolithic Encyclopedia Prompts vs. a 30-Line Directory-Pointer Index (3.13x Faster)

Eliminating Print-Debugging Loops in Coding Agents: Bare Stack Traces vs. Runtime Frame Variable-Snapshot Injection (-95.0% Input Tokens)

Why Hand-Written Example Tests Fail AI Coding Agents: Fixed Sample Tests vs. a Property-Based Invariant Fuzzing Sensor (-95.1% Input Tokens)

Why Coding Agents Need a Pre-Submit Diff Audit Gate: Blind Unchecked Submits vs. Blast-Radius & Entropy Auditing (-95.0% Input Tokens)

Stop Letting Coding Agents Do Manual Multi-Spot String Replacements: Manual Text Edits vs. Parameterized AST Codemod Tools (-94.8% Input Tokens)