Wal @walidshaari

A new agentic research model and harness called AREX checks its answers requirement by requirement, keeps what's verified, and researches only the gaps. 📰✅ 📊 82.5% BrowseComp, 82.0 F1 WideSearch-en 📈 Harness alone: up to +10 pts 🧠 Fine tuned 4B beat untuned 35B on 5 of 6 benchmarks hubs.la/Q04ztJKG0 #DeepLearningAI #AIAgents #LLMs

Figure 1-20 is the most important figure out of the 330+ in An Illustrated Guide to AI Agents. 1- It shows what today's LLM-based AI agents are composed of, including their user and environment loops. 2- It is also therefore a table of contents for Part 1: Agent Fundamentals, showing where each of the key components is explained in details. Read it here: Amazon: amazon.com/Illustrated-Gu… O'Reilly: learning.oreilly.com/library/view/a… PDF e-book: ebooks.com/en-ca/book/347…

Someone gave Jev a crawler + one GPT agent and asked: “Where is the online money right now?” It read 5,137 open jobs and found 3 niches where clients are paying and almost nobody is bidding. Everyone asks ChatGPT for side hustle ideas. Everyone gets the same 10 answers. This approach is different. The crawler reads what clients are actually paying for. Jev analyzes thousands of jobs cheaply and GPT only gets called when something looks worth researching. The result: 01. Chrome extensions → $545 median, 11 bids/job 02. TikTok Shop setup → $232 median, 6.5 bids/job 03. Notion setup → $181 median, 3 bids/job Jev made 9,617 calls for $0.13. GPT alone would have cost ~$58.66. The whole run cost $6.53. The interesting part isn’t even the 3 niches. It’s the architecture: Crawler → Jev filters → Jev ranks → GPT researches → real opportunities Cheap model does the volume. Expensive model only handles the work that needs deeper reasoning. That’s a much more interesting way to use AI for finding opportunities. x.com/paonx_eth/stat…

Arindam Majumder 𝕏 @Arindam_1729

4 weeks ago

x.com/i/article/2103…

5 10 61 213K 166

whoever built this realized we’ve been using our smartest AI for the dumbest possible jobs your $20-$200/mo frontier model is researching, writing code, planning… and then you’re paying the same brain to decide YES / NO. Jev flips that. it’s a tiny decision model that sits in front of the expensive stuff and handles the boring forks: -> which agent goes next? -> is this worth researching? -> reply or ignore? -> publish, wait or escalate? -> BUY / SELL / HOLD? -> click this or keep looking? then I saw the numbers people are reporting and the whole architecture started making a lot more sense. ~1,000 papers classified for around $0.08 ~500 emails sorted for around $0.035 browser-agent loops demonstrated around 7 seconds for ~$0.0039 and at the quoted pricing, roughly 10,000 ~1K-token decisions comes out around $0.42. that’s not because Jev became smarter than Claude. it’s because nobody asked it to be Claude. the setup is stupidly simple: -> big LLM gets the hard thinking, research and writing -> Jev gets the thousands of tiny decisions between those steps -> code actually clicks, saves, sends and executes and suddenly you start noticing these little decisions everywhere. > your inbox. > X feed. > support queue. > meetings. > leads. > video clips. > browser agents. > even paper-trading loops. that’s the part I think most agent builders are missing. the expensive model doesn’t need to touch every step just because it’s capable of touching every step. > let Claude think. > let Jev decide what deserves Claude. > let code do the actual work. I broke down 12 places you can wire this into an agent today + the exact router setup in the article below

kiosa @thegreatest_sv

4 weeks ago

x.com/i/article/2102…

22 77 444 1.2M 1K

We turned Claude Code, Codex, Hermes, Pi, @opencode and other coding harnesses into RL environments. No changes to the harnesses, no changes to the training code. Any open model, any task set, fully open source my friends! Same model, same weights: 62% under Mini-SWE-Agent, 33% under Claude Code. But training inside a real harness normally means reimplementing it as an environment, so most models get trained in a scaffold nobody actually ships. The fix is a proxy, not a rewrite. The harness thinks it's talking to a model API. It's actually talking to a capture proxy that speaks the 4 formats coding agents use (OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, Gemini), forwards to @vllm_project, records the exact token IDs and logprobs vLLM sampled, and hands TRL sequences it can train on. The harness becomes the environment. 10 harnesses run through it today, none modified. And because you control the reward, you can shape behavior the harness never asked for. We added a small bonus for solving a task in fewer tool calls: on tasks it already solved, the model now uses 31% fewer calls, in every harness, and about half under Codex. Tested on LFM2.5-2.6B from @liquidai: → Train in one harness: better mostly in that harness (OpenCode 34% → 58%). → Train in 4 at once: better in all 4 (42% → 54%). → SFT on 3,189 rollouts from Qwen3.8-27B instead: plateaus at 47.5%, below both RL runs. Everything is open and reproducible: the capture proxy in OpenEnv, the trainer in TRL, the tasks, the SFT data, the training code and all 7 trained models. Bigger models and bigger runs next. Full guide: huggingface.co/spaces/FineEnv…

x.com/i/article/2103…

Handbook on Understanding Harness Engineering for AI Agents [48-page PDF]: drive.google.com/file/d/1PT-P2P…

Industrial software doesn’t have to feel like industrial software Manage warehouses like you’re playing a strategy game Built with Opus 5.5

found this free Harness Engineering course on GitHub with 14 lectures + 8 hands-on projects. it covers: > how Claude Code, Codex, DeepSeek build their harness > loop & graph engineering > automated agent loops > observability, testing and verification really good source for learning harness essentials by doing. github.com/walkinglabs/le…

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-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

What does it take to be a great FDE at OpenAI - we get this question alot, so I sat down with @gregorojstersek to talk about how we’ve built the team, what the work looks at, and the values we want the team to have - always make the thing exist (and work) first, then look for scale second. We talk through a few of the recent focuses in how we operate - we've got a bigger focus on domain experts than we used to, and ultimately success for us revolves around working to replace ourselves in every customer problem we take on. Check out the interview below, and if you're interested in the role then I've included the careers page too - look forward to seeing what you build! Interview: newsletter.eng-leadership.com/p/inside-opena… FDE careers: openai.com/careers/search…

NEVER FORGET this HERO!

X Global @X_Global_tv

4 weeks ago

🚨 BREAKING: The U.S. deported Chinese student Liu Lijun for supporting Palestine.

445 5K 36K 5.0M 1K

NVIDIA/Model-Optimizer: A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc.

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with @qdrant_engine and taught by @DylanCouzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the DeepLearning.AI mobile app. Enroll for free: hubs.la/Q04y3S0F0

介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！ github.com/mizorewww/laya…

Local Laya moggs Jev at @grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally -> atomic.chat

雨夹雪❄️ @mizorewww

a month ago

介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！ github.com/mizorewww/laya…

295 1K 14K 4.3M 18K

oh snap. finishing quick used to be a bad thing 💅

TypeSafe AI @typesafeai

a month ago

Jev is now available to everyone. No waitlist. Start using it here: console.typesafe.ai

741 2K 23K 3.2M 12K

Over 300 original figures! An Illustrated Guide to AI Agents is now OUT on Kindle and other Ebook stores! Presses are rolling, print copies ship in a few weeks. @MaartenGr and I spent the last year and a half making the agent stack legible: memory, tools, planning, evaluation, multi-agent systems, and code agents. We're ecstatic to finally be able to share it with you! Agents are being adopted faster than they're being understood. Our bet is that a small number of concepts will outlast everything else in this field, so we spent the time identifying them and explaining them properly. Concepts and code. You build a working agent yourself along the way. Order here: Amazon: amazon.com/Illustrated-Gu… O'Reilly: oreilly.com/library/view/a…

This just gets crazier by the second. @Meta and @finkd need to address this ASAP. This is the flock-fueled future everyone is afraid of and corporations keep telling everyone it's fine. Prove it. @ kontheinside on IG

Opus or Sonnet? Maybe that’s the wrong question. Claude is becoming more than a model—it’s becoming an AI operating layer. The real edge in 2026? Not the best model. The best AI stack.