| | Evals before prompts: building an LLM OCR for KYC (nilenso.com) |
| 1 point by priyangapkini 68 days ago | past | 1 comment |
|
| | Building the systems that build the software (nilenso.com) |
| 3 points by ath_ray 3 months ago | past |
|
| | Training a small model to write better OCaml with RLVR and GRPO (nilenso.com) |
| 2 points by sriharis 4 months ago | past |
|
| | How the Lobsters front page works – nilenso blog (nilenso.com) |
| 2 points by fagnerbrack 5 months ago | past |
|
| | Trajectory shapes are work habits (nilenso.com) |
| 3 points by sriharis 5 months ago | past |
|
| | Checking my model vibes against SWE-Bench Pro (nilenso.com) |
| 3 points by sriharis 5 months ago | past |
|
| | Weird System Prompt Artefacts (nilenso.com) |
| 2 points by sriharis 7 months ago | past |
|
| | Feature Platforms: The Underrated Infrastructure Layer Behind Fast ML Teams (nilenso.com) |
| 2 points by sriharis 7 months ago | past |
|
| | Engineering Maturity is all you need (nilenso.com) |
| 2 points by sriharis 7 months ago | past |
|
| | Codex CLI vs. Claude Code on Autonomy (nilenso.com) |
| 1 point by ath_ray 7 months ago | past |
|
| | Weird System Prompt Artefacts (nilenso.com) |
| 1 point by ath_ray 7 months ago | past |
|
| | Minimum Viable Benchmark (For Evaluating LLMs) (nilenso.com) |
| 1 point by todsacerdoti 9 months ago | past |
|
| | Minimum Viable Benchmark (nilenso.com) |
| 1 point by ath_ray 10 months ago | past |
|
| | Taste and Adjust (nilenso.com) |
| 3 points by sriharis 10 months ago | past |
|
| | How to work with product: To what port do you sail? (nilenso.com) |
| 3 points by sriharis 10 months ago | past |
|
| | How to work with Product: At the tea table (nilenso.com) |
| 3 points by sriharis 10 months ago | past |
|
| | A Short Lesson in Simpler Prompts (nilenso.com) |
| 3 points by sriharis 11 months ago | past |
|
| | Fight context rot with context observability (nilenso.com) |
| 3 points by sriharis 11 months ago | past |
|
| | Show HN: A tool to properly observe your LLM's context window (nilenso.com) |
| 8 points by ath_ray 11 months ago | past |
|
| | Artisanal shims for the bitter lesson age (nilenso.com) |
| 4 points by todsacerdoti 11 months ago | past |
|
| | What are popular AI coding benchmarks measuring? (nilenso.com) |
| 3 points by birdculture on Sept 27, 2025 | past |
|
| | What are popular AI coding benchmarks measuring? (nilenso.com) |
| 3 points by todsacerdoti on Sept 25, 2025 | past |
|
| | The common sense unit of work (nilenso.com) |
| 4 points by sriharis on Sept 22, 2025 | past |
|
| | The common sense unit of work (nilenso.com) |
| 30 points by todsacerdoti on Sept 19, 2025 | past | 3 comments |
|
| | The quality of AI-assisted software depends on unit of work management (nilenso.com) |
| 170 points by mogambo1 on Sept 18, 2025 | past | 123 comments |
|
| | My Quarterly System Health Check-In (nilenso.com) |
| 3 points by Bogdanp on Sept 10, 2025 | past |
|
| | My Quarterly System Health Check-In: Beyond the Dashboard (nilenso.com) |
| 21 points by sriharis on Sept 9, 2025 | past | 2 comments |
|
| | Why does AI feel so different? (nilenso.com) |
| 56 points by ath_ray on Aug 13, 2025 | past | 101 comments |
|
| | How I keep up with AI progress (nilenso.com) |
| 284 points by itzlambda on July 18, 2025 | past | 118 comments |
|
| | How I keep up with AI progress (nilenso.com) |
| 2 points by Bogdanp on July 15, 2025 | past |
|
|
| More |
