AirAi Ecological Partnership Plan: Give up a $10,000 quota to sponsor people who are still making things
...
Claude
I reduced the cost of the LLM API by 70%: Practical notes on using AirAi with routing and caching
0. Background: How did the costs explode?I work on several side projects. In the early stages, I either had to pay the official subscription fee of /month or endure the rejections when trying to use international credit cards. When I settled the accounts at the end of the month, I discovered two frustrating issues:80% of the requests were for simple tasks such as summarizing, categorizing, and formatting data. Using the most expensive models for these tasks was a complete waste;The subscription fee is a fixed cost – it results in losses when there are few requests, and it’s not enough when there are many requests.
We used Claude 3 Opus to process cross-border customs declaration forms, which saved us 60% on manual review costs, but we encountered three pitfalls along the way.
We used Claude 3 Opus to process cross-border customs declarations, which saved 60% on manual review costs, but we encountered three issues
Claude secretly becomes stupid while doing AI research, and Anthropic is besieged by the research community
Claude Fable 5 is the main focus in the AI field today; this “mythical” model performs exceptionally well and has attracted tremendous attention.Andrej Karpathy described it as “very exciting” and an “evolutionary step that deserves a major version upgrade,” on par with the improvements brought by Claude 4.5 last November. In the SWE-bench Pro programming benchmark, Fable 5 achieved a score of 80.3%, which is 11 percentage points higher than Opus 4.8. With a Ruby codebase consisting of 50 million lines of code, Fable 5 completed the entire codebase migration in just one day; if the same task were assigned to a human team, it would take more than two months.
The rapidly heating Voice AI competition has seen the emergence of a startup team called Hojo.
Voice AI represents another narrative that unfolds alongside the development of general large models. While everyone is focused on the general large models, the relatively quieter field of Voice AI is also seeing the emergence of some noteworthy new models. The keyboard is starting to lose its “dominant position.” Over the past two years, OpenAI introduced the Realtime API, Google launched Gemini Live, and domestic large-model companies have almost all begun to invest in Voice AI. More and more people believe that once agents truly integrate into workflows, voice will become a more natural way to interact with systems than using a keyboard. For an agent to truly become part of a workflow, it must first learn to understand human speech. The foundational capability for this is ASR (Automatic Speech Recognition). The most commonly used benchmark for measuring ASR performance is Hugging Face’s Open ASR Leaderboard, which uses the Word Error Rate (WER) as a key indicator. The lower the WER, the more accurate the recognition.
No More