SSevenindaoxe-notes.hashnode.dev·1d ago · 9 min readWe pointed our model-honesty probe at our own gateway. It said SUSPICIOUS.Posted first on DEV.to at https://dev.to/seven7763/we-pointed-our-model-honesty-probe-at-our-own-gateway-it-said-suspicious-58o5 We built a CLI tool that gives you signals about whether an LLM API en00
SSevenindaoxe-notes.hashnode.dev·2d ago · 9 min readTen questions to answer before you route production traffic through someone else's LLM endpointPosted first on DEV.to at https://dev.to/seven7763/ten-questions-to-answer-before-you-route-production-traffic-through-someone-elses-llm-endpoint-oml Every LLM endpoint's landing page says fast, reli00
SSevenindaoxe-notes.hashnode.dev·2d ago · 10 min readFive coding agents, one endpoint: where the base URL field actually livesPosted first on DEV.to at https://dev.to/seven7763/five-coding-agents-one-endpoint-where-the-base-url-field-actually-lives-3cka Every one of these tools supports a custom OpenAI-compatible endpoint. 00
SSevenindaoxe-notes.hashnode.dev·Sep 7 · 10 min read"OpenAI-compatible" is a spectrum, not a boolean — a conformance checklistTwo endpoints both say "OpenAI-compatible" on the tin. You point your app at the first one and everything works. You point it at the second one and everything works too — for about a week. Then a stre00
SSevenindaoxe-notes.hashnode.dev·Sep 4 · 3 min readLobeChat в Docker + один ключ к нескольким моделям: как это собрать и что видно в логахLobeChat в Docker + один ключ к нескольким моделям: как это собрать и что реально видно в логах Руководство на русском: поднять собственный чат-клиент за пять команд и подключить к нему несколько LLM 00
