Knowledge catalogue
Huge if true! We are talking about a 27B multimodal model that runs locally on a phone. That's wild! Bonsai 27B reaches up to 163 tok/s in 1-bit and 134 tok/s in Ternary on an NVIDIA GeForce RTX 5090.
New research from Google DeepMind on effective model routing. LLM routers get judged on accuracy and cost. Both can look great while the router is meaningless. If every model in your society responds
You can now use Claude inside After Effects. Higgsfield's new MCP connector lets Claude work inside your actual AE project. It can build compositions, set keyframes, write expressions, and run the rep
// An Anatomy of CLI Coding Agent Trajectories // (bookmark it) When your coding agent fails a task, when did the run actually go wrong? Most reliability studies use the final label to answer this. Th
Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (@hyperagentapp) as a reusable s
Another big reason to use combination of frontier models. Chain-of-thought monitoring is treated as a reliable safety layer for agents. This DeepMind-affiliated study shows the layer can be argued out
Cool open-source release. LingBot-World 2.0 holds 720p at 60 fps in real time and stays coherent for a full hour of interaction. A 1.3B variant runs on a single consumer GPU, so you can actually run a
This post highlights a practical AI agent that operates intuitively without requiring explanation of its underlying mechanics, suggesting it has achieved a user-friendly interface or autonomous functi
New research from Meta. (bookmark it) It's on how to fix agents that forget previously made decisions. It's well know that long-horizon agents keep forgetting decisions they already made. Meta researc
This post discusses positive experiences with GPT-5.6's capabilities in verification, advisory functions, and high-level orchestration tasks, suggesting the model performs better than expected in thes
A Visual Introduction to Information Theory (bookmark it) Information Theory is such an beautiful and powerful subject. In the era of AI, it's worth spending time learning about it. Here is a highly-r
Here is my other heavily used pattern. Evaluator/Judge: Fable 5 Executor: GPT-5.5 I no longer wait for frontier models or am loyal to any. I now spend more time on better orchestration, harness, skill
Is Meta AI back? Haven't seen Mark post in three years here. Plus, the model is available via API. Not to mention the courage to announce it the same week as the long-awaited GPT-5.6. Great timing if
Muse Spark 1.1 available in new Meta Model API. Somewhere near Opus-4.8/GPT-5.5 level. 1M context window! Computer-use capabilities sound great: Write scripts when automation is faster, click when dir
// The Harness Effect // (bookmark it) Now more that ever pay very close attention to the orchestration harness and its effect on costs and performance. This study ran 22 evaluation tasks on six found
Claude power users: 'Fable 5 is the best' Codex power users: 'GPT-5.6 is the best' Reality: Loyalty to a single model provider is a terrible strategy. The smart choice: clever orchestration between fr
Great writeup from the University of Oxford. It's a taxonomy of LLM-based agent limitations. Good read for anyone shipping with agents. Benchmark scores keep climbing, yet the same agent failures resu
Highly-recommended read. Aligns with what I see in my own harness: > Pi harness got the same success rate as harnesses from the LLM vendors with Opus and GPT, but at 2x less cost > GLM 5.2 was a major
I am more excited to try this pattern instead. Same Executor-Advisor setup but with GPT-5.6 as the executor and Fable 5 as the advisor. It already works wonderfully using GPT-5.5, so I think 5.6 shoul
Massive open-source release! LingBot-Video isn't about video quality; it optimizes for physical reasoning, and it runs sparse: only 3B of 30B params are active at inference. MoE is finally showing up
// Memory becomes an action space // Great paper on long-term memory for agents. (bookmark it) In short, it's discusses the use of a learned policy for using memory at the right granularity. Most memo
Nice stats on usage of open models across OpenCode. GLM-5.2 is still underrated, but one of the models that has really surprised me on agentic tasks is deepseek-v4-flash. Extremely cheap and effective
Banger compression paper from NVIDIA. (bookmark it) Bigger MoE models keep winning on quality, but serving them at interactive latency is still hard. NVIDIA compresses the hybrid MoE Nemotron-3-Super
Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. M
// MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and leave how it improves frozen and hand-authored. That improvement procedure never
NEW AI paper worth bookmarking. This is something I called early, and this paper confirms it: verification has emerged as a new important scaling axis. Here is the simple explainer and what this paper
The release of Fable 5 just points to the importance of agent orchestration. You really don't need Fable 5 for most tasks. You can plan with Opus 4.8/Fable 5, execute with GPT-5.5, and design with GLM
Absolutely. And protect your expertise as much as you can in this new era of AI. Learn to package it as a product or experience using AI. I find that content creation is one of the highest ROI activit
Cool open-source release. Physical AI is the next frontier, so things are shifting from thinking to taking action. LingBot-Vision looks like a strong visual foundation model and shows progress in cons
'Ghost memory' is a real problem with agents. You might have seen the issue where a long-running agent still confidently repeats a user fact that stopped being true weeks ago? New research names the f
// In-context Retrieval at Million-token Scale // Great study providing better understanding of retrieval at million-token scale. They run the first systematic study of in-context retrieval at the sca
Must-read research by Anthropic. Here is the simple explanation and why this is a big deal. We suspect LLMs perform 'internal reasoning'. But little is known or do good methods exist to understand it.
// ReContext // Models now support 128K context windows and still fail to use evidence that is already in the prompt. Where is the gap? New paper introduces ReContext, a training-free inference harnes
// What MCP, A2A, and ACP cannot express // MCP and A2A solve capability discovery and message passing, then stop right where enterprise deployment begins. New research runs a systematic gap analysis
Fable 5 is an absolute beast at threejs. It's the best LLM at generating 3D simulations/worlds. Watch how I combine it with gpt-realtime-2 to generate interactive educational 3D worlds @dair_ai. Comme
Great overview of always-on agents. (bookmark it) It's a new 130+ pages survey on always-on agents. Simply put it, always-on agents are systems whose future behavior depends on durable state built up
// HASTE: tiered skills for ML engineering agents // Why do ML engineering agents keep rediscovering the same techniques on every new task? Because each competition is a cold start. New research intro
The Top AI Papers of the Week (June 28 - July 5): - RLMF - AutoMem - Paper Assistant Tool - MCP Server Patterns - The Verification Horizon - Red Queen Gödel Machine - Generative Skill Composition Read
Multimodal prompting enhances coding agents by enabling them to process and integrate multiple types of input data—such as text, images, and code snippets—simultaneously, improving their ability to un
This post discusses the evolution of multimodal prompting in AI agent interactions, highlighting how users can now communicate with AI systems using multiple input types beyond text. The author provid
Can coding-agents replicate scientific ML papers? We know this is possible because we can already do this @dair_ai. Still a great read. So they try to replicate an ML paper from its materials alone. T
Highly-recommended read from MIT on the part of RL with verifiable rewards that everyone keeps hitting. RLVR only optimizes what you can objectively score, so style, structure, and diversity quietly c
Multimodal prompting is clearly the future. I love experimenting with new ways to interact with agents. As a researcher and engineer, I've found that the richer the inputs to the agent and the richer
NEW paper worth reading. (bookmark it) The basic idea is to pair a compressive recurrent state with a small exact memory, which helps to recover long-range recall without giving up the efficiency of l
AI sovereignty isn’t optional. Don’t give away your alpha so easily. Protect it as much as you can. Open source models are critical and should be an important part of any individual’s, organisation’s,
Another fascinating paper on LLM Judges. (bookmark it) It's from Amazon, and they show that if you run panels of LLM judges, averaging their scores is a trap. 'Overall, we establish that robust aggreg
// AutoMem // I quite like this idea of metamemory. (bookmark it) This new research from Stanford treats agent's memory management as a trainable skill instead of a fixed module. The model decides wha
LLM Wikis are being slept on. I argue that creating knowledge bases with LLMs or coding agents is one of the most valuable applications of AI today. It's about being intentional in building and scalin
NEW paper from NVIDIA. They discuss robot programming that compounds experience instead of throwing it away. Traditional robot programming forces you to orchestrate perception, contact dynamics, diver
New research from Google. LLMs hallucinate with high confidence, miss their own knowledge boundaries, and misreport uncertainty. Most fixes bolt calibration on from the outside. RLMF turns the model o
Great paper on managing agent skills. Skill libraries keep growing, and picking the right skills has become a bottleneck for coding agents. The defaults are to expose the agent to the whole skill coll
My prediction: the excitement for Fable 5 will wear off really fast. Reposting this to help those who will be extremely disappointed after they play with Fable 5 and run out of tokens or can't do much
NEW paper worth reading. (bookmark it) Autonomous research systems usually prove themselves on cherry-picked wins, human-framed topics, or a handful of preset tasks. FARS runs the full loop at scale i
Really confused by all the excitement I see in my timeline for a nerfed model. Never seen anything like it. So many will end up very disappointed. Time to rethink how to build around frontier and open
This post compares the outputs of three AI models—GLM-5.2, Fugu Ultra, and Fable 5—using an identical one-shot prompt to evaluate their performance, with the author expressing a preference for Fable 5
Cool new paper from NVIDIA. Looks like agentic coding is moving into hardware design. HORIZON treats hardware design as repository-level code evolution. A Markdown harness becomes a project pack with
If you build with MCPs, this one is worth reading. (bookmark it) The paper covers five recurring MCP server patterns across fifteen independently developed servers. That taxonomy is useful because I s
Love how Google continues to drive down the cost of building with their models. <4s image and 0.034 / 1K image. Wow! We have a bunch of stuff (education & research) we're building @dair_ai using Nano
// Neural procedural memory // Good paper on agent memory beyond prompt retrieval. NPM stores procedural skills as activation steering vectors distilled from contrastive historical experience. Textual
Qwen publishes new work on RL coding agents. (bookmark it) The idea is to continually build a verification system that co-evolves with AI agents. LLMs suffer from all sorts of reward hacking issues. T