Dmitri Hrapof

AI-First Lisp Architect at IgniteTech

[Dmitri Hrapof @hrapof3292]

@JonnyValleyBoy 😖

[Vik Paruchuri @VikParuchuri]

We made a fair OCR benchmark. And we're not ranked first.

Introducing OmniParseBench - 16k tests across 90 languages with consistent, interpretable scoring.

[Dmitri Hrapof @hrapof3292]

@Nekrolm Best database system manager?

[Dmitri Hrapof @hrapof3292]

@grahamscheper Nid ydych! Prydeinwyr sy'n arnoch! 🤣

[Dmitri Hrapof @hrapof3292]

@ChShersh I'm implementing a cache in COBOL now 😁

[Vik Paruchuri @VikParuchuri]

I've been training OCR models for 2 years. The progress we've made in handwriting is astonishing - from barely readable to almost perfect transcription.

[Dmitri Hrapof @hrapof3292]

@burkov Hearing levels? Наверно, "уровни заголовков"?

[Dmitri Hrapof @hrapof3292]

@ChShersh @aas_ker

[Anton Lobach @AntLobach]

Chez Scheme: almost no libs for web dev available, and then all of a sudden, this masterpiece

https://t.co/la77Hrsc3F

[Chi Wang @Chi_Wang_]

Anthropic says its first Fermat runs failed not on math, but because dozens of Claude agents lost track of shared project state. They only succeeded after moving to Prove2Me's DAG of statements and proofs. At that scale, "memory" must be external, structured infrastructure, not prompts.
https://t.co/NxpAib7LAg

[Dmitri Hrapof @hrapof3292]

@WiciCymru 😓

[Dmitri Hrapof @hrapof3292]

@ChShersh Трай Бесы 😈

[Dmitri Hrapof @hrapof3292]

@ChShersh В отпуске, небось 🤞

[Google Research @GoogleResearch]

Introducing TimesFM-3, a state-of-the-art time series foundation model that enables accurate multivariate time series forecasting in a single forward pass, significantly outperforming other forecasting models across major benchmarks.

More on the blog →https://t.co/uSlnIdUJ4Q

[Dmitri Hrapof @hrapof3292]

@MabinogionGame I like to think Mabinogi's Caswallawn is Caesar's Cassiuellaunos 😀

[Dmitri Hrapof @hrapof3292]

@WiciCymru @simongerman600 😥

[Dmitri Hrapof @hrapof3292]

@lisperati Blind Guardian 🤘

[Unsloth AI @UnslothAI]

GLM-5.3 can now be run locally!

The 2-bit model retains ~81% accuracy after we shrunk it from 1.51TB to 239GB (-83% size).

Run on a 256GB Mac or RAM/VRAM setups.

GLM-5.3 is the strongest open model to date.

Guide: https://t.co/NLgb3CMB6A
GGUF: https://t.co/Sqwq3xjgo5