NVIDIA Dynamo is a reality check on the broken economics of agentic coding
NVIDIA is rebuilding the inference stack with KV-aware routing because traditional architectures cannot survive the hidden cost of agentic API loops.
Tag archive
Infrastructure
Everything we’ve published under Infrastructure so far.
Follow this lane
5 Useful Machines posts on Infrastructure
Infrastructure appears in infrastructure and deployment, a useful buying-intent lane for relevant AI products and services.
GPT-5.5 is in the API. Stop rewriting your retry logic.
OpenAI pushed GPT-5.5 to Chat Completions and Responses with a 1M context window, while putting GPT-5.5-pro behind Responses. The real product is fewer retries — and a nudge off legacy chat endpoints.
Perplexity makes GPT-5.5 its orchestration default, because tool-calling is the only benchmark that matters
Perplexity is deploying GPT-5.5 as the default orchestrator for its agentic tier. It proves the next phase of AI architecture is a barbell: heavy routers delegating to cheap generators.
Google Gemini 3.1 TTS introduces audio tags to end the retry tax
The introduction of inline audio tags in Gemini 3.1 TTS isn't just a formatting trick. It is a fundamental shift from probabilistic guessing to deterministic steering, aimed directly at the hidden costs of inference.
Google’s new TPUs prove that agentic AI is mostly a billing problem
Google’s TPU 8i and 8t announcement sounds like a hardware story. It's actually a confession that AI agents turn latency and serving costs into your biggest product bottlenecks.