Mistral OCR 4 turned a handwritten calculus exam into clean LaTeX!
We gave it a photo of a hand-written exam page. The model read the handwriting and rebuilt every formula into structured digital text
Output: Time: 5.1s · Cost: $0.09
Formulas came through exactly right - the hard part was nailed. The graph, unfortunately, it didn’t redraw. But that’s the telling part: most OCR tools just dump the text and quietly drop the figure. OCR 4 caught the plot, boxed it, and tagged it as a chart. It doesn’t get redrawn, but it gets read and accounted for
Ask Claude to document and describe the main flows in your app and output in a single page html + json data file.
Incredibly useful for humans and the JSON file is very useful for explaining the flow to the LLM when working on new features/bugfixes.
Introducing Files SDK
A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. An escape hatch when you need the native client.
→ 18 providers - S3, R2, Vercel Blob, Google Drive, etc.
→ upload, download, head, delete, copy, list, url
→ Works everywhere - Node, Bun, Deno, edge runtimes, browsers
→ Tools for OpenAI, Vercel AI and Claude Agents SDKs
@trq212 I wholeheartedly concur. However, considering the significant readability achieved with Python code, don't you believe HTML code is also in dire need of a substantial overhaul?
New Anthropic research: Natural Language Autoencoders.
Models like Claude talk in words but think in numbers. The numbers—called activations—encode Claude’s thoughts, but not in a language we can read.
Here, we train Claude to translate its activations into human-readable text.
I just joined Ethos — where top experts get matched to opportunities. If you're serious about your craft, you should be here too: https://t.co/XEDgukilKT