Pawel Bojkowski

LLM hacking at 3:00 am / Father / Husband / Mr. Hustle / Technology enthusiast / Security enthusiast / Entrepreneur

[Pawel Bojkowski @pbojkowski]

Found the chap I need to share all the Nvidia H100s with at night‼️‼️

BTW: Awesome work! @futuristfrog

[Bob @futuristfrog]

I code at 3:00 am because everyone else is sleeping so ChatGPT is faster. We are not same

[Claude @claudeai]

Introducing Claude Opus 4.7, our most capable Opus model yet.

It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.

You can hand off your hardest work with less supervision.

[Pawel Bojkowski @pbojkowski]

ASI will be smarter than a civilization of Einsteins

[Pawel Bojkowski @pbojkowski]

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems

Abstract:
While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying.......

https://t.co/nK2HvG3J5q

[Pawel Bojkowski @pbojkowski]

A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces

Abstract:
Frontier language models have demonstrated strong reasoning and long-horizon tool-use capabilities. However, existing RAG systems fail to leverage.....

https://t.co/IUkXD9Nm6l

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

PROTECC OPUS 4.6 AT ALL COSTS

🪄 THE MAGIC IS BACK ✨

[Pawel Bojkowski @pbojkowski]

InfMem: Learning System-2 Memory Control for Long-Context Agent

Abstract:
Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable

https://t.co/Anl5zpYS0r

[Pawel Bojkowski @pbojkowski]

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Abstract
Agent memory systems often adopt the standard Retrieval-Augmented Generation (RAG) pipeline, yet its underlying assumptions differ in this setting. RAG targets large.........
https://t.co/4wn5zqn2Oe

[Pawel Bojkowski @pbojkowski]

Nice!

[Pawel Bojkowski @pbojkowski]

Scaling Multiagent Systems with Process Rewards

Abstract:
While multiagent systems have shown promise for tackling complex tasks via specialization, finetuning multiple agents simultaneously faces two key challenges..............

https://t.co/qx66Wa7LkU

[Pawel Bojkowski @pbojkowski]

Building a C compiler with a team of parallel Claudes

We (Anthropic) tasked Opus 4.6 using agent teams to build a C Compiler, and then (mostly) walked away. Here's what it taught us about the future of autonomous software development.

https://t.co/I3UdezGKwr

[Claude @claudeai]

Introducing Claude Opus 4.6. Our smartest model got an upgrade.

Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes.

It’s also our first Opus-class model with 1M token context in beta.

[Alex Patrascu @maxescu]

Kling 3.0 is here!

And it comes with two game-changing updates:
Kling 3.0 and Omni 3.0

Features:
- 3-15s with multi-shot sequences
- Native audio with multiple characters
- Upload/record video character as reference + consistent voices

Available now on @higgsfield_ai

[Tom Warren @tomwarren]

Anthropic just took a big swipe at OpenAI's decision to put ads in ChatGPT. Anthropic is airing ads mocking ChatGPT ads during the Super Bowl, and they're hilarious 😅 Anthropic is also committing to no ads in Claude https://t.co/LR1v4xz9ds

[Pawel Bojkowski @pbojkowski]

Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems

Abstract:
The emerging field of diverse intelligence seeks an integrated view of problem solving

https://t.co/NsWGP2WAik

[Pawel Bojkowski @pbojkowski]

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Abstract:
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure......

https://t.co/fpE1qosaIv

[Pawel Bojkowski @pbojkowski]

Agentic Reasoning for Large Language Models

Abstract:
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world...

https://t.co/tRPsY454dA

[Pawel Bojkowski @pbojkowski]

https://t.co/dXCji40R9r

[Pawel Bojkowski @pbojkowski]

🔥This is HOT🔥

Dario Amodei - The Adolescence of Technology

https://t.co/QqQY9zKYkS

[Pawel Bojkowski @pbojkowski]

SimpleMem: Efficient Lifelong Memory for LLM Agents

Abstract:

To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full....

https://t.co/oCLMa61ZoA

[Pawel Bojkowski @pbojkowski]

Active Context Compression: Autonomous Memory Management in LLM Agents

Abstract:

Large Language Model (LLM) agents struggle with long-horizon software engineering tasks due to “Context Bloat.” As interaction history grows, computational costs explode...

https://t.co/lHlbUU6qZ2