Archive

Typesafe AI Daily, October 11, '26

Cloudflare tries to make agent decisions explicit while Databricks, Pydantic, LadybugDB, DataFusion, and the lakehouse crowd tighten the data contracts underneath.

Typesafe AI Daily, October 10, '26

Cloudflare pushes agent infrastructure toward explicit choices, while Databricks, Pydantic, DataFusion, LanceDB, NVIDIA, OpenAI, and Crunchbase show the same fight moving through databases, schemas, hardware, and capital.

Typesafe AI Daily, October 9, '26

Cloudflare pushes agents toward bounded decisions, while Databricks, NVIDIA, ServiceNow, LanceDB, and new benchmarks tighten the evidence around state, schemas, and deployment cost.

Two rivers, one road: Rust and OxCaml race to count meanders

We ran the verified meander-counting machine as fast as two languages could take it. OxCaml took the lead, our first explanation was wrong, and one experiment let Rust catch up and count 50 crossings.

Typesafe AI Daily: Cloudflare Open Sources Decision Models for AI Agents

A wider newsroom scan found 12 strong signals across AI infrastructure, funding, research, and developer tools.

How many ways can a river cross a road? Counting Arnold's meanders with proofs

Arnold asked in how many ways a river can cross a road n times. Nobody has a formula, so we counted the rivers with programs proved correct in Lean 4: every value up to 32 crossings, a paper on First Pair, and a film.

Typesafe AI Daily, October 7, '26

Managed agent runtimes, schema-constrained tools, and local data engines are becoming the real battleground for enterprise AI.

TPC-DOOM: how fast does your SQL database run Doom?

TPC-DOOM measures the speed of the fastest databases

Sail plays Doom: SQLDoom's own client at 32 tics a second on Spark SQL

Best Spark jobs. Best SQL Doom. On Rust.

Typesafe AI Daily, October 6, '26

DigitalOcean turns agent hosting into governed runtime infrastructure, while Microsoft, ServiceNow, Pydantic, DataFusion, and Delta Lake sharpen the contract between AI claims and data truth.

Typesafe AI Daily: The Agent Said It Was Done. The Database Disagreed

A wider newsroom scan found 12 strong signals across AI infrastructure, funding, research, and developer tools.

Anthropology Math

EIgen Times, Anthropology, and their math form a new teaching method, First Pair.

Anthropology Math

EIgen Times, Anthropology, and their math form a new teaching method, First Pair.

Typesafe AI Daily, October 5, '26

Agent stacks are leaving demo land: the news is costed workflows, typed decisions, microVM isolation, and data engines that can prove what happened.

Typesafe AI Daily, October 4, '26

The database is becoming the judge of agent work: Microsoft’s ThinkingBox post, DigitalOcean’s managed agent runtime, and schema-heavy releases from Pydantic and BAML all point at the same operational demand.

Typesafe AI Daily, October 2, '26

DigitalOcean turns agent deployment into a managed runtime question while ServiceNow, OpenAI, NVIDIA, Databricks, LanceDB, and TypeSafe AI push on data, speed, cost, and typed outputs.

Typesafe AI Daily, October 1, '26

Typed outputs move from prompt hygiene to model interface, while agent infrastructure funding follows durability.

Typesafe AI Daily, September 30, ’26

Cloudflare makes JavaScript build speed look like agent infrastructure, while OpenAI case studies, LanceDB’s physical-AI data push, and new database-policy research tighten the case for typed boundaries.

Nutmeg 0.1.0: graph algorithms where the data already is

Grust's graph kernels inside Sail's Spark Connect server: stage a graph from a DataFrame, call an algorithm, get a DataFrame back.

Grust Langoustine: narrower graphs, cheaper accounting, and scores you can ask for in f32

Grust's latest backend-neutral property-graph release.