19 Jul 2026, 20:35 UTC≈8,550 views13 reactionsread 6 August 2026 Photo
The internet has accumulated a lot of knowledge in the form of PDFs. Some of these are digital-native PDFs, while others are just wrappers around images. Until now, there hasn't been much demand for parsing these PDFs in a structured way.
Document parsing has become much more popular in recent years. We wanted to leverage all that accumulated data to train our LLMs. This fueled interest in building OCR systems that …
👍9🔥4
19 Jul 2026, 19:58 UTC513 views4 reactionsread 6 August 2026 https://www.linkedin.com/posts/bnhop_we-run-our-coval-stt-benchmark-every-30-minutes-ugcPost-7483956231968018432-cVqB/?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAzP3TIB4pvnEUAvi_ABR6D5qCr_LxAIk0s
Btw folks, follow her to get interesting Voice AI related stats weekly. She is a Ex-Tesla, and currently building a coval.ai, voice ai eval solution.
❤3🔥1
1 Jun 2026, 21:37 UTC897 views8 reactionsread 6 August 2026 https://www.youtube.com/watch?v=xOP1PM8fwnk
One of the best explanations of how current Video Gen models are built.
This is very interesting space to be in. You learn how H264\265 codecs are built. How to leverage the hybrid of Autoregressive and Diffusion models to build a time series of images. (Video is series of images over time + Audio).
The video quickly touches FFT (Fast Fourie Transform) as well. FFT is a f…
🔥6❤2
5 May 2026, 20:36 UTC≈1,210 views8 reactionsread 6 August 2026 https://www.youtube.com/watch?v=kYkIdXwW2AE
If you are aware, Yann LeCoun has left Meta and actively researching/developing and investing in other startups that are trying to move frontier in NON-LLM directions. Yann isinvesting / betting on World Models (Generic name).
He thinks LLMs are not the best proxies of the way Human intelligence works.
On this video, Yann is sharing his thoughts on JEPE models. Problems o…
👍5⚡3
18 Apr 2026, 04:14 UTC≈1,380 views49 reactionsread 6 August 2026 Photo
AGI is here folks! Holly cow!
Claude Opus 4.7 did it!
😁44👍5
3 Mar 2026, 11:49 UTC≈2,320 views22 reactionsread 6 August 2026 Photo
So true. There is not much MOAT in software anymore.
I bet we are gonna see lots of Software companies start adding Hardware products to create a defensibility very soon.
👍22
10 Feb 2026, 22:04 UTC≈1,940 views25 reactionsread 6 August 2026 Video
My laziness hit a new rock bottom :).
Now Claude Code is reading its output out loud:).
So I don't have to read small text out of my screen all the time :).
Local TTS
https://github.com/ktaletsk/claude-code-tts#
🤣19🔥4👍2
10 Feb 2026, 16:53 UTC≈1,400 views6 reactionsread 6 August 2026 We are hiring from Uzbekistan
🔥6
8 Feb 2026, 23:04 UTC≈1,390 views31 reactionsread 6 August 2026 Video
I became overly dependant on Claude Code lately. I appreciate the fact that Claude Code shows a horizontal green indefinit progress bar at the top of my terminal, but that is so easy to miss the point when ClaudeCode is done with my task or it wants my input to go forward.
Apparently you can use hooks to play sound :). So, what I did was, I asked claude the following:
Change my claude hook sound effects to the war…
🤣30👍1
2 Feb 2026, 07:38 UTC≈1,930 views5 reactionsread 6 August 2026 STEP-3.5-FLASH: Breaking the Speed vs. Intelligence Trade-off
StepFun released a model with 196 billion parameters, but only 11 billion activate per token. This is a sparse Mixture-of-Experts model. The model is performed pretty well on SWE-Bench. People are claiming that to be GPT-4 level quality which is pretty good based on my experience.
Its throughput is 300 tokens per second on modern hardware. Compare that …
🔥5
31 Dec 2025, 03:49 UTC≈1,470 views28 reactionsread 6 August 2026 Video
We are living in a world where
- Resumes are generated by GenAI,
- Applications are submitted by AI agents
- Replies are written by AI agents :)
😁13🤣8👍4❤2🔥1
21 Dec 2025, 23:42 UTC≈1,760 views7 reactionsread 6 August 2026 https://www.youtube.com/watch?v=-Tgc_9uYJLI
Thisis a big leap forward in On-Device / Edge infrence. This model can work directly on your devices or browser.
Our Agents @Numeo have to have lots of skills/instructions. This comes with its challanges. You probably have heard about "Curs of Instructions" paper that explains why having too much instructions is bad.
At Numeo we have been doubling on building our Agents i…
🔥4❤3
Showing the 12 most recent of 19 posts we hold for @coder_off_blog. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.