| | Ralph (danluu.com) |
| 2 points by tosh 20 hours ago | past | discuss |
|
| | There's no point at which turning your brain off will work (danluu.com) |
| 202 points by robin_reala 4 days ago | past | 156 comments |
|
| | Agentic test processes, LLM benchmarks, and other notes on agentic coding (danluu.com) |
| 3 points by admp 8 days ago | past | discuss |
|
| | Bad benchmarks and evals: Senior SWE-Bench, napkin math, and winter tires (danluu.com) |
| 56 points by luu 12 days ago | past | 46 comments |
|
| | How well do agents use test/verification techniques? (danluu.com) |
| 191 points by vinhnx 15 days ago | past | 71 comments |
|
| | How well do agents use test/verification techniques? (danluu.com) |
| 7 points by tosh 15 days ago | past | 1 comment |
|
| | How accurate have Ed Zitron's AI skeptic predictions been? (danluu.com) |
| 879 points by jatins 21 days ago | past | 1056 comments |
|
| | Bug Blindness (danluu.com) |
| 407 points by davidmckenna 24 days ago | past | 287 comments |
|
| | Developer Hiring and the Market for Lemons (danluu.com) |
| 2 points by rzk 28 days ago | past | 2 comments |
|
| | Bad benchmarks and evals: Senior SWE-Bench, napkin math, and winter tires (danluu.com) |
| 1 point by luu 29 days ago | past |
|
| | There's no reason for software to be slow anymore (danluu.com) |
| 669 points by Jach 32 days ago | past | 499 comments |
|
| | HN: The Good Parts (2016) (danluu.com) |
| 82 points by adletbalzhanov 32 days ago | past | 23 comments |
|
| | Bad benchmarks and evals: Senior SWE-Bench, napkin math, and winter tires (danluu.com) |
| 2 points by yosefk 35 days ago | past |
|
| | The Benchmarkpocalypse (danluu.com) |
| 183 points by cyndunlop 36 days ago | past | 64 comments |
|
| | Agentic test processes, LLM benchmarks, and other notes (danluu.com) |
| 2 points by kqr 43 days ago | past |
|
| | What's the best programming language for coding agents? (danluu.com) |
| 262 points by chaychoong 43 days ago | past | 188 comments |
|
| | How do programming languages impact token efficiency and correctness? (danluu.com) |
| 18 points by matt_d 44 days ago | past | 1 comment |
|
| | Exercises in benchmarking and evals, part 7: DeepSWE, Senior SWE-Bench (danluu.com) |
| 3 points by ndr 56 days ago | past |
|
| | Exercises in benchmarking and evals, part 7 (danluu.com) |
| 1 point by janvdberg 57 days ago | past |
|
| | Agentic test processes, LLM benchmarks, and other notes on agentic coding (danluu.com) |
| 17 points by bathtub365 59 days ago | past | 1 comment |
|
| | I could do that in a weekend (2016) (danluu.com) |
| 20 points by ntumlin 64 days ago | past | 4 comments |
|
| | Agentic test processes, LLM benchmarks, and other notes from Galapagos Island (danluu.com) |
| 2 points by gnyeki 65 days ago | past |
|
| | Agentic test processes, LLM benchmarks, notes on agentic coding from Galapagos (danluu.com) |
| 1 point by FabHK 74 days ago | past |
|
| | Why don't schools teach debugging? (2014) (danluu.com) |
| 2 points by bmacho 74 days ago | past |
|
| | Agentic test processes, LLM benchmarks, and other notes on agentic coding fr (danluu.com) |
| 20 points by lifeisstillgood 76 days ago | past | 2 comments |
|
| | Agentic test processes, LLM benchmarks, and other notes on agentic coding (danluu.com) |
| 1 point by ndr 77 days ago | past |
|
| | Agentic test processes, LLM benchmarks (danluu.com) |
| 2 points by eatonphil 80 days ago | past |
|
| | Diseconomies of scale in fraud, spam, support, and moderation (danluu.com) |
| 4 points by Liriel 81 days ago | past | 3 comments |
|
| | Agentic coding notes (danluu.com) |
| 179 points by gm678 81 days ago | past | 83 comments |
|
| | 95%-ile isn't that good (2020) (danluu.com) |
| 2 points by bmacho 83 days ago | past | 1 comment |
|
|
| More |
