Datalab released OmniParseBench, an open OCR document-parsing benchmark that evaluates parsers using auditable yes/no tests across tagged slices. It includes 16,288 pass/fail tests on 2,937 pages from 2,343 documents across 92 languages. Results can now be run and sliced offline by tag and suite, replacing leaderboard-only comparisons with a more targeted “which parser handles my documents” evaluation.
Craft Agents launches as fully open-source AI workflow automation software that runs locally and can use multiple AI providers. It is described as launching today. As a result, users can connect the agents to tools like MCP, APIs, and local files to produce diffs, tables, diagrams, and schedule automations in a desktop UI.
Relace open-sourced its training and evaluation approach for Fast Apply models after releasing its first public Fast Apply model a year ago and improving code-merge inference. Relace Apply 3 is designed to run at 10k+ tokens per second after generating mergeable diffs and applying them with a specialized model. This changes how coding edits are produced and merged by splitting diff generation from a fast apply step, using an LLM-as-a-judge pipeline to train a smaller merge model on ~145k filtered examples.
developers.googleblog.com·4 days ago·
7
● 20 sources
Google engineers ran Gemini 4 Argon on the google/adk-python codebase overnight to find and fix cross-file performance bottlenecks and produced a pull request with proposed framework optimizations. It cut ADK in-memory session prep time by about 40% in long sessions and reduced cold package import time by 21%. After maintainer review, 2 of 6 proposed optimizations were shipped to production while 4 were rejected for issues like fragility, extra complexity, or synthetic-only gains.
Every AI story that matters,
in your inbox by 8am.
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the
day in two minutes. Follow companies and topics for alerts, or get the
briefing in Slack. Free, no spam, unsubscribe anytime.
Reading TLDRocket needs no cookies, and the readership counts we rely on come from
our own cookieless analytics. Google Analytics is the exception: it sets cookies and
reports to Google, so it stays switched off until you allow it. You can change your
mind any time from “Cookie settings” in the footer.
Strictly necessary
Session security and form protection (tldrocket-session,
XSRF-TOKEN, 2 hours). The site cannot work without them,
so they need no consent.
Always on
Google Analytics 4 (_ga,
_ga_<id>, up to 2 years). Measures which
stories and sections readers use. Google acts as a third-party processor and may
store the data outside the EU. No advertising, no profiling, no data sold.
