Search: “llm”

This works really well btw, at the end of your query ask your LLM to 'structure your response as HTML', then view the generated file in your browser. I've also had some success asking the LLM to prese

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and

The LangSmith Signal report analyzes API call volume and developer adoption trends across major LLM providers, leveraging LangChain's open-source data and observability platform to track usage pattern

Nice paper on optimizing agents and their graders together. The key finding is that you want to update your LLM grader alongside the agent instead of keeping it fixed, because the agent's failure mode

Sometimes everybody is right! Me, spring 2023 onwards: giving LLM-driven agents unrestricted internet access with read/write permissions is going to be a security nightmare. The AI industry: Agents ar

Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa

Brilliant paper on long-horizon agents. They cut 78.9% of an agent's LLM calls while raising its success rate. Here is how: It turns out that ReAct issues one primitive action per model round. That al

This is one of the most useful writeups I have seen on keeping an LLM judge effective in production. (bookmark it) Netflix runs judges over hundreds of thousands of show-level recommendation explanati

// Skill Misevolution in Self-Improving LLM Agents // Self-improving agents write their successes down as reusable skills. An unsafe success becomes reusable policy long after the input that triggered

Big new release of my LLM CLI tool and Python library for talking to hundreds of different LLMs - reasoning traces, OpenAI Responses support, server-side tools, smarter logging and a whole lot more ht

We're starting to leave the territory where you'd test an LLM by e.g. 'create an svg of pelican on a bicycle'. As one idea to generalize it, I was interested what Opus 5 would do if I gave it the firs

Finally a good paper testing if file-system based memory for LLM agents is worth it. First, what does this look like? Deployed agents keep long-term memory as a folder of markdown files they read and

A fun AI video effect to try: balance on top of a moving animal while pulling off impossible tricks. This ComfyUI workflow uses an LLM to generate the right Seedance 2.0 prompts, making it easy to rec

A fun AI video effect: ride a living animal like it's a skateboard. This ComfyUI workflow uses an LLM to generate optimized Seedance prompts, making the effect easy to recreate without all the prompt

LLMs are stateless (every time you reply to an LLM, you re-inject the entire conversation to a fresh inference) the purpose of memory is to provide continuity (in games we'd call it a 'persistent worl

The pure LLM debate - which I had for many years, here and elsewhere - is indeed no longer relevant. Why? Because I won; nobody uses pure LLMs anymore. Nowadays all deployed objects are neurosymbolic,

When an LLM acts happy (“EUREKA!”) or sad (“I have failed…”), is that meaningless mimicry, or does it reflect something “real”? We don’t know if LLMs are conscious. But they increasingly seem to exhib

1/5 When we saw our Reducer (=LLM judge component in Maestro, our agentic framework, that selects the best output from parallel agent runs) consistently picking gold patches, we were sure Claude Opus

3/5 An example: In instance psf__requests-1724, the gold fix is 2 lines. Our agent’s functional fix was 8 lines. The LLM judge rejected the correct 8-liner as 'messy' and 'redundant,' choosing a clean

5/5 The takeaway: If your agent relies on an LLM judge for selection accuracy, measuring code quality isn’t enough; you need a measure of the model's inductive bias toward the 'fingerprint' of a gold

I looked at their prompts, It's complete bs They are literally providing all of the insight to the LLM upfront > Are there any security vulnerabilities in this code? Consider the behavior of the SEQ_L

Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's LLM agents must write out every reasoning step as text before they can search, run code, or take acti

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

Remember October 2022 when you doused Galactica with vitriol? Galactica was a 120b-parameter LLM-based system from Meta-FAIR designed to help scientist write papers. It was open sourced (link below).

Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the

I have absolutely never ever 'asked' to stop R&D on LLMs. In fact, I was very supportive of LLM efforts at Meta. Just look up my public advocacy for Galactica (November 2022), and the open sourcing of

jev as a Judge proves to be a cheaper and more precise alternative to LLM as a judge for online evals. great guide from Sean and Daniel on why Jev is great for evals, an experiment vs other LLMs, and

What happens if you agents to run a town's economy? This super interesting paper provides some insights: They put 100 LLM agents in charge of a town economy for 26 simulated weeks, and they find that

Wild paper from Microsoft and colleagues. They show a new attack that reconstructs the text a local LLM generates by watching CPU cache activity while it detokenizes. Earlier cache attacks needed some

Finally a good paper testing whether an LLM's mathematical knowledge has coherent structure or just coherent accuracy. There is a lot of interest in using LLMs for advancing math. This is a great read

Simon @disiok proposed a novel IQ test for language models, asking whether an LLM becomes smarter or dumber after being fine‑tuned on a user’s stream of consciousness. The tweet was posted on 9 Aug 20

Zain (@zainhas) published a detailed article on August 7, 2026 explaining that autoscaling for highly peaky large‑language‑model (LLM) inference is fundamentally different from autoscaling conventiona

Finally a good paper testing whether agent memory needs an LLM at all. Production memory stacks spend extra model calls on summarizing interactions, writing records, and reranking retrievals. Every on

Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning, calling tools, and self-correcting across long multi-turn

'The paper's insight connects to a broader pattern: AI agents are essentially distributed systems with unreliable components (the LLM), and we should apply distributed systems patterns to them.' https

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

The most important part of an AI agent isn't the LLM. It's what surrounds it. 👇 The first image made it click for me. While exploring LangChain Deep Agents, I ran the same prompt. Same model. Almost t

This is what latency optimization looks like below the API 👇 Together ATLAS, NVIDIA Blackwell, CUDA, TensorRT-LLM, Dynamo, and custom kernels all working together to make inference faster for users. P

LLM-as-a-Judge explained in ~10 mins. Knowing how to build AI verifiers and judges is one of the most important emerging AI skills today. Here is a quick intro on the topic and where to learn how to a

shoutouts: • why multi-agent LLM systems fail? (arXiv:2503.13657) — @mertcemri @melissapan + @istoica05 @matei_zaharia @profjoeyg @adityagp & team • DSPy (arXiv:2310.03714) — @lateinteraction + @hazyr

This is really intellectually dishonest. I have not been arguing that LLM token prices are increasing (though the all you can eat buffet is over), I have been arguing the *opposite*, viz that they wil

Cost controls are one of the main benefits of langsmith LLM gateway We’re seeing in a bunch of use cases adoption is getting to a point where cost really starts to matter Your agents can burn through

It's been *almost* a bit quiet around LLM architecture releases in the past two weeks 😅 Interesting tidbit is the parallel block design. Via the Cmd-A the tech report 'equivalent performance but signi

we've been building agents around the llm, starting with conversations, adding tools, giving rules, logging everything, and storing a form of it as retrievable state Active Graphs flips this. what if

LLM apps fail in ways normal logs can’t explain. Same input, different outputs. Subtle drift. Silent hallucinations. That’s the problem space LangSmith by @LangChain was built for: observability + eva

🚨Breaking new study: memory in LLM agents still can’t really be trusted, even after over trillion dollars has gone into the development of the field. Excited to share our new paper: “Useful Memories B