Fatih⏩⤴️ (@taskinfatih) 's Twitter Profile
Fatih⏩⤴️

@taskinfatih

Lover of all novel and hard concepts: especially machine learning and systems theory

ID: 12109752

calendar_today11-01-2008 11:07:05

15,15K Tweet

556 Followers

4,4K Following

Kubilay Yıldırım (@hepdurgunsu) 's Twitter Profile Photo

Önce Rusya, sonrasında İran… Yetişmiş, ülkesine bağlı insan gücünü kovalamış, yitirmiş, herkesi “işbirlikçi/komprador” gören, kendi dar çıkar çevresine sıkışmış, halkı sefalete sürüklenen, fukaralığın propagandası yapılan ülkelerde nükleer mükleer işe yaramıyor.

Fatih⏩⤴️ (@taskinfatih) 's Twitter Profile Photo

I have not used API yet but I am trying it on web app (gemini.google.com/app) and windsurf/cursor so no thinking budget. As a side effect, model's prompt adherence or instruction following also deteriorate. Just as an example: when I prompted for PRD with earlier version, it

Percy Liang (@percyliang) 's Twitter Profile Photo

Wrapped up Stanford CS336 (Language Models from Scratch), taught with an amazing team Tatsunori Hashimoto Marcel Rød Neil Band Rohith Kuditipudi. Researchers are becoming detached from the technical details of how LMs work. In CS336, we try to fix that by having students build everything:

Weaviate • vector database (@weaviate_io) 's Twitter Profile Photo

Multi-vector search is beating agentic RAG by miles. But they come at a cost. Or do they? Recently, new multi-vector models like Reason-ModernColBERT have outperformed popular reasoning-based retrieval models like ReasonIR-8B. The embedding-per-token approach of ColBERT style

Multi-vector search is beating agentic RAG by miles.

But they come at a cost. Or do they?

Recently, new multi-vector models like Reason-ModernColBERT have outperformed popular reasoning-based retrieval models like ReasonIR-8B. The embedding-per-token approach of ColBERT style
Paweł Huryn (@pawelhuryn) 's Twitter Profile Photo

RAG is the most critical part of context management in AI. But doing it right is tough. I created a free, interactive simulator that visualizes different variants: 🧵

Orion Weller @ ICLR 2025 (@orionweller) 's Twitter Profile Photo

🤔 Have you ever wondered how good ModernBERT is compared to decoders like Llama? We made an open-data version of ModernBERT and used the same recipe for encoders and decoders. Turns out, our encoder model beat ModernBERT and our decoder model beats Llama 3.2 / SmolLM2 🤯 🧵

🤔 Have you ever wondered how good ModernBERT is compared to decoders like Llama?

We made an open-data version of ModernBERT and used the same recipe for encoders and decoders.

Turns out, our encoder model beat ModernBERT and our decoder model beats Llama 3.2 / SmolLM2 🤯

🧵
Midnight Maniac Sri (@sridatta) 's Twitter Profile Photo

'water is transparent only within a very narrow band of the electromagnetic spectrum, so living organisms evolved sensitivity to that band, and that's what we now call "visible light". ' (found via HN)

'water is transparent only within a very narrow band of the electromagnetic spectrum, 

so living organisms evolved sensitivity to that band, and that's what we now call "visible light". '

(found via HN)
Jimmy Apples 🍎/acc (@apples_jimmy) 's Twitter Profile Photo

So before people take credit, I found the oai os a min after they uploaded and saved the config and other stuff before it was removed. It’s an OS model and coming soon so kinda feels like ruining a surprise

So before people take credit, I found the oai os a min after they uploaded and saved the config and other stuff before it was removed.

It’s an OS model and coming soon so kinda feels like ruining a surprise
Greg Trayling (@gregtrayling) 's Twitter Profile Photo

Today's library addition: A new (2024) history book on how we arrived at the current notation for vectors and general tensors, with an early nod to the quaternion approach and how things could have gone another route.

Today's library addition: A new (2024) history book on how we arrived at the current notation for vectors and general tensors, with an early nod to the quaternion approach and how things could have gone another route.
Z.ai (@zai_org) 's Twitter Profile Photo

Presenting the GLM-4.5 technical report!👇 arxiv.org/abs/2508.06471 This work demonstrates how we developed models that excel at reasoning, coding, and agentic tasks through a unique, multi-stage training paradigm. Key innovations include expert model iteration with

Presenting the GLM-4.5 technical report!👇
arxiv.org/abs/2508.06471

This work demonstrates how we developed models that excel at reasoning, coding, and agentic tasks through a unique, multi-stage training paradigm.

Key innovations include expert model iteration with
Craig Murray (@craigmurrayorg) 's Twitter Profile Photo

The percentage of child dead in the Ukrainian conflict is 0.3%. Zero point three per cent. The percentage of child dead in the Gaza conflict is 37.7%. Thirty seven point seven per cent. In a single statistic, there you have the difference between a war and a genocide.

Ant Ling (@antling20041208) 's Twitter Profile Photo

We open-source Ring-flash-2.0 — the thinking version of Ling-flash-2.0. --> SOTA reasoning in math, code, logic & beyond. --> 100B-A6B, 200+ tok/s on 4×H20 GPUs. --> Powered by "icepop"🧊, solving RL instability in MoE LLMs.

We open-source Ring-flash-2.0 — the thinking version of Ling-flash-2.0.
--> SOTA reasoning in math, code, logic & beyond.
--> 100B-A6B, 200+ tok/s on 4×H20 GPUs.
--> Powered by "icepop"🧊, solving RL instability in MoE LLMs.