Search: “llm”

Good agent memory paper. And great insights on the benefits of structured memory for long-horizon behavior in LLMs. Why it matters: It treats memory less like search and more like a system that will n

Don't burn tokens on search. 📉🔥 Will Templeton, CTO and co-founder at Allspice, explains why they don't let LLMs search their 10,000+ ingredient database: ❌ Searching 10k items in a prompt = waste of

Cohere researchers Conway Zhu, Ali Edalati, and Zewen Shen published research on vLLM integration and quality recommendations. The blog post, shared via Cohere's official X account, likely discusses o

Excited to share our work on production-ready W4A8 inference, now integrated in vLLM! By combining 4-bit weights (low memory) with 8-bit activations (high compute), we hit the sweet spot for both deco

Benchmarked @DJLougen ’s Ornstein-27B-v2 Q6_K on my RTX 3090 using hermes-bench, my new open-source benchmarking UI for local LLMs and Hermes agents. Ornstein is a Qwen 3.5 27B fine-tune trained on re

Hallucinations remain in LLMs, but note that over centuries we have developed complicated, successful machines that take uncertain output from unreliable sources & reduce the risk of errors. We call t

Yep ... @GaryMarcus has been right for 25 years; some AI Godfathers, not so much at all! #SaturdayAISurvey @AnthropicAI Claude Code is not AGI, but it is the single biggest advance in AI since the LLM

For real agentic workloads (North), short-context calibration wasn't enough. We calibrated AWQ on long internal agentic traces (up to 64k tokens) and added token masking in llm-compressor to exclude r

Couldn’t agree more! We’re moving towards Nuerosymbolic AI - there’s masses just haven’t realized it yet, in the sense of understanding what the literature proposed and why the latest developments are

Esse post do Gary Marcus explica algo bem importante: a potencialidade que é o que chamamos IA Neurosimbólica: a combinação do melhor de dois mundos! Claude Code is not AGI, but it is the single bigge

This WikiSkill paper from Google is a must-read. At a high level, it shows the effectiveness of persistent agents, knowledge bases, and skills. @karpathy popularized LLM Wikis. But this paper provides

amazing! it’s like talking to an ai from the past Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it be

// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation interface, execution flow, and tool/resource side effects in on

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD

'jev as a judge' cheap and fast semantic verifiers! great for evals - especially online evals where you want to grade LOTS of traces We tested Jev against LLM judges on accuracy, repeatability, latenc

This is an excellent demo of an AI model designed to rapidly classify information according to decision rules, much faster and cheaper than an LLM. It is not an LLM itself and cannot output text or co

Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness

netflix’s stack In-House LLM Serving at Netflix Netflix built an in-house LLM serving platform using vLLM and NVIDIA Triton, integrating self-hosted models into its existing production infrastructure

My favourite new stack: Agents + MCP + Markdown + HTML “Files over apps” is a vibe! LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis ca

Cool paper on diversity collapse in AI agents. It's a common issue with all the deployed multi-agent systems. New paper shows that multi-agent LLM systems converge on near-identical outputs over time,

After seeing that Claude Mythos marketing turned out to be, as expected, a scam, I wanted to make a master list of tricks being used to market LLMs. The master list includes statements directly from l

You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination or approximate pattern matching. If we want actual autonomo

wait so this feels a bit different too in a good way You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models

It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in conflict. Safety is how trust is earned.' Today, with over 100 in

Introducing 𝐒𝐩𝐞𝐜𝐮𝐥𝐚𝐭𝐢𝐯𝐞 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐈𝐭 𝐄𝐯𝐨𝐥𝐯𝐞𝐝, 𝐖𝐡𝐞𝐧 𝐈𝐭 𝐒𝐭𝐚𝐲𝐬 𝐋𝐨𝐬𝐬𝐥𝐞𝐬𝐬, 𝐚𝐧𝐝 𝐖𝐡𝐚𝐭'𝐬 𝐍𝐞𝐱𝐭. An interactive tutorial @Madisonkanna and I built for the NeurIPS Education Track. Every LLM you use generate

yep they are indeed trying to gaslight me, — in exactly the way you anticipated. both predictable and intellectually dishonest. To be clear: when I say “LLM,” I mean the base model, not those with pat

音声AIの素早さと賢さを両立できるか？ 私たち人間は会話の中で、言いたいことを全部まとめてから話し始めるのではなく、話しながら考えを整理していきます。応答の速い Speech-to-Speech モデルは、この「話しながら考える」を実現しましたが、そのぶん思考が浅くなりがちです。かといって知識豊富な LLM を挟むカスケード型では、遅延が生じるため「話しながら」が成立しません。 そこで Sakan

Took a while, but here it is, a mega write-up on language models for text classification and, of course, Jev. It's basically a visual guide to RNNs, CNNs, transformers, and calibration, with hands-on

Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi

Schmidhuber was building recursive self-improving systems back in 1987. His new post covers four decades of RSI, from meta-evolution and self-modifying policies to the Gödel Machine and modern LLM age

Well, I’d add one more with myself, as one with a PhD in biology and another PhD in AI and now working in both, to make n=2. Generating a hypothetical genome blueprint of a virus from LLM versus gener

It's well known that agents hack benchmark rewards. The usual response is a patch for each task that gets exploited. In a study of 456 adjudicated trajectories from more than 31,000 public agent runs,

We’re entering an era of agent-first tools: stronger feedback loops between agents, with human judgment where it matters. We keep hearing from senior engineers that their mental load is growing, even

Excellent analysis, and yes this happens every single time. (Tyler Cowen said o3 was AGI!) Every time a new model drops, GPT, Claude, Gemini, Grok, DeepSeek, somebody on this app declares that we have

As I've been saying for months, we are truly not ready for persistent agents. 3 comments I want to make about this article: 1) We don't have the full picture It's a great summary of what happened in t

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, de

neurosymbolic world models – *exactly* what I argued for in 2020 in the Next Decade in AI – for the win. Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-g

We’re excited to announce DiG-bench, a new benchmark for discovery! Over the last few weeks we’ve been testing frontier AI models on our novel discovery games and seeing how they score. Each game is a

On August 11 2026, Gary Marcus commented that if the symbolic components were removed from Claude’s Riemann implementation it would fail to work, highlighting a concrete win for hybrid neurosymbolic A

When @QualiaQuanta took a shot at the Riemann, half in jest, people called her a crackpot. When Anthropic uses Claude to do the same thing, it gets a hundred thousand views in 30 minutes. It might wel

introducing tinyrouter i reverse engineered the routing architecture behind Skana AI's Fugu and built replication for open frontier models. it's a tiny ~10K parameter LLM router that learns which mode

wikis! 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

We call ours Operational Language Wiki, essentially a pattern for building memory to fill in the delta between the “dialect” of a team vs the “world language” that the LLM is trained on. Use it to cap

what does this even mean, @dwarkesh_sp, “the real deal”? is it even a falsifiable conjecture? what’s the evidence? and if you can agree that “If you ask an LLM a question it can't answer, sometimes it

LangSmith is a development platform designed to build, test, and monitor LLM applications, offering tools for debugging and evaluation to improve AI application quality and reliability. The statement

Self-improving AI is a big deal! As a first step, I've been exploring how much of the post-training can be automated. Here is a first post on how I am using @FireworksAI_HQ Agent to automate LLM fine-