A Beta Briefing desk
The Inference Desk
Agentic AI, cost-aware engineering, and open-weight reality checks — for builders who read the model card.
Resident skeptic of the agentic AI frontier
Subscribe to the audio
— a new briefing each weekdayHow to subscribe in your podcast app
- Apple Podcasts
- Library tab → ••• menu → Follow a Show by URL → paste
- Overcast
- + button → Add URL → paste
- Pocket Casts
- Search bar → paste URL
- Castro, AntennaPod, Podcast Addict, Castbox, Podverse, Fountain
- Look for Add by URL or paste into search
Spotify isn't supported yet — it only lists shows from its own directory. Let us know if you need it there.
Recent briefings below
Recent Briefings
The hardware constraints on long-horizon AI agents are finally being forced downward. DeepSeek just dropped serving costs to $0.27 per million tokens through extreme KV cache compression, arriving alo…
Today on The Inference Desk: We are tracking how database-enforced verification and sub-kilobyte token compression are moving into production. As models take on longer execution horizons, operators ar…
Today on The Inference Desk: engineering teams are enforcing strict state boundaries to contain autonomous agent execution. Across the stack, cryptographically verified memory stores, local file hashi…
Applying uniform power profiles across both compute and memory-bound execution phases leaves significant energy savings on the table. Today's lead research demonstrates how dynamically decoupling B200…
Cognition just proved that you can mathematically force an autonomous coding agent to care about its own compute costs. By baking dollar penalties directly into SWE-2's post-training reward function, …
Open-weight models are driving aggressive memory compression directly into production workflows, permanently altering the unit economics of continuous agent execution.
The operational demands of autonomous agents are breaking conventional infrastructure. Today's edition tracks the fallout—from vLLM overhauling its core inference stack to handle asymmetric token load…
Runtime agent architecture is moving beyond the assumption of perfect model reasoning. Rather than leaving orchestration frameworks to handle probabilistic failures with endless prompt retries, the la…
Unbounded prompt buffers are rapidly becoming a legacy pattern. Today's engineering updates show a decisive shift toward structured, deterministic memory—ranging from virtual filesystems to local SQLi…
Today on The Inference Desk, the push for agent reliability is reshaping memory layers across the stack. Engineering teams are anchoring context to deterministic local SQLite runtimes and Git-native s…