antoniohttps://antonio.fika.bar/The "DeepSeek V4 Flash + GLM-5.2" Combination Is Currently Enough for Me (and Will Probably Be Enough for You Too)https://antonio.fika.bar/the-deepseek-v4-flash-glm-5-2-combination-is-currently-e-01KYAS156XMFCBWKP87AWHBEGQhttps://antonio.fika.bar/the-deepseek-v4-flash-glm-5-2-combination-is-currently-e-01KYAS156XMFCBWKP87AWHBEGQWhy a well-balanced AI stack beats relying on the most expensive modelFri, 24 Jul 2026 13:00:00 GMTGLM-5.2: I thought Sonnet 4.5 and similar open models were enough, but…https://antonio.fika.bar/glm-5-2-i-thought-sonnet-4-5-and-similar-open-models-were-e-01KYARQJR5C80QV5AHRDN7Y3KXhttps://antonio.fika.bar/glm-5-2-i-thought-sonnet-4-5-and-similar-open-models-were-e-01KYARQJR5C80QV5AHRDN7Y3KXHow GLM-5.2 Redefined What I Consider Sufficient for DevelopmentThu, 25 Jun 2026 13:00:00 GMTAgentic AI, SLMs, and Why Models Above US$0.50 Output per 1M Tokens Are Equivalent to Burning Moneyhttps://antonio.fika.bar/agentic-ai-slms-and-why-models-above-us-0-50-output-per-1m-01KYARDZM5H1ME5S4SAJ53PBF2https://antonio.fika.bar/agentic-ai-slms-and-why-models-above-us-0-50-output-per-1m-01KYARDZM5H1ME5S4SAJ53PBF2By an IITM student, researcher, and agentic AI enthusiast who got tired of paying absurd amounts for ChatGPT and Claude subscriptionsTue, 16 Jun 2026 13:00:00 GMT