InTowards AIbyChew Loong Nian - AI ENGINEER·1d agoClaude Code Missed $800K in Contracts. Here’s How to Check YoursAn AlixPartners talk showed how messy contract data fooled Claude Code. In 510 real contracts, 18% auto-renew with a notice period, so the…A response icon1A response icon1
Chew Loong Nian - AI ENGINEER·1d agoHow to Catch GPT and Llama Making Up NumbersA response icon2A response icon2
Chew Loong Nian - AI ENGINEER·3d agoClaude Doesn't Need "Think Step by Step" Anymore. Here's What to CutAnthropic’s Lance Martin says old prompt habits now cost tokens and quality. I turned Claude Code’s own audit checklist into a free script…
InTowards AIbyChew Loong Nian - AI ENGINEER·4d agoA Netflix Scientist Says Resample Your LLM Judge. 5 Runs Cut the Error Bar 13%A response icon1A response icon1
InTowards AIbyChew Loong Nian - AI ENGINEER·5d agoWhy Cheap Kimi Agents Only Beat GPT-5.5 on a Small BudgetRamp ran GPT-5.5, Kimi K2.6 and DeepSeek V4 Pro 25 times each on 7 real security bugs. For the same money at 5x, Kimi finds 4.06 bugs on…A response icon1A response icon1
InTowards AIbyChew Loong Nian - AI ENGINEER·6d agoYour Claude Agent Costs 9x More Without Prompt CachingA response icon1A response icon1
Chew Loong Nian - AI ENGINEER·Nov 3How to Stop Claude Code From Deleting Your Production DatabaseA valid Railway token let an AI agent wipe a database in 9 seconds. Railway’s API has 233 write calls; a “delete” deny-list catches 47. A…
Chew Loong Nian - AI ENGINEER·Nov 1Excel Files Your AI Agent Writes in Python Have No Numbers in Them
Chew Loong Nian - AI ENGINEER·Nov 1Why DeepSeek's Super Agent Listens to Anyone Who Comments on Its PRs