Solving a Million-Step LLM Task with Zero Errors
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans,...
The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities (Version 1.0)
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges…
Optimizing Agentic Workflows using Meta-tools
Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations,...
There continue to be reasons for software to be slow
A discussion on the various reasons why performance is slow, and which ones are unlikely to be affected by LLMs. Originally written as a counter-point to Dan Luu
Extensible Software in the age of LLMs | Jeremy Morrell
Solid core + capability-based sandboxes + LLMs = Users with superpowers
open-slopware
Free/Open Source Software choosing to use and/or support LLM usage/AI, as well as alternatives and tips to requesting better policies or forking.
MCP servers vs. skills: Choosing the right context for your AI | Red Hat Developer
Large language models (LLMs) are efficient general-purpose tools, but they work much better when you give them the right context
Build agents, not pipelines
There are only two ways to use LLMs in a computer program: as part of a pipeline, or as an agent. In other words, either you express the control flow of the program in code, or you give a LLM tools and allow it to manage the control flow itself1.
Sebastian Raschka on Twitter / X
Pretty cool. I think 2025-2026 will be a stronger focus on these in open source tooling.I.e. having LLMs delegate knowledge-based queries to search, which in turn frees up model capacity to improve reasoning capabilities and tool use. https://t.co/wNTg283mb2— Sebastian Raschka (@rasbt) August 12, 2025
Instant LLM Updates with Doc-to-LoRA and Text-to-LoRA
Recent LLM agents have shown impressive capabilities on complex computer use and long-horizon tasks. Yet, they still struggle with long-term memory and adaptation--two of the most important cognitive capabilities that still limit LLMs today. Without long-term memory, users have to provide LLMs with relevant content at the start of every new session, creating friction, discontinuity, and longer time-to-response. Additionally, due to the lack of adaptation, they do not learn from mistakes or user preferences from previous sessions, making each interaction as cumbersome as the first. Traditionally, these two problems are tackled by "updating" the model.
I accidentally turned LLM memory into program analysis :: pwning.systems
Why I stopped trying to give LLM agents a better memory and instead built Lemmalog, a Datalog engine that maintains an agent's knowledge as analysis state, with provenance, retractions and incremental evaluation, plus what happened when I benchmarked it on LongMemEval and LoCoMo.
LLMs are not like manufacturing machines - Ross Wintle
LLMs are not just machines. They are machine-building machines! This comes with way more responsibility. And understanding it may change how you use them.
