←
patrick614 posts
patrick avatar

patrick

@patrickamadeus_

phd @mbzuai | multimodal in research & life.

◷ Joined November 2020▧ 82 Photos and videos
patrick avatar
patrick@patrickamadeus_·Nov 17

really looking forward to their upcoming research!

Through my wonderful time at NVIDIA and Stanford, one question has kept me up at night: Should the future of AI be monolithic or plural? To answer this question, we’ve raised $110M to get started, backed by @MenloVentures, @MadronaVentures, @NVIDIA, @NEA, @KindredVentures,@Wing_VC, @aixventureshq, @Principal_VC, @Cisco, @Snowflake, among others. Today, Carlos (@guestrin) and I are stoked to launch Noeri, a neolab to push the frontier of plural intelligence. Noeri means “the plural of intelligence” or many intelligences. The future of AI we root for is plural: a healthy ecosystem of many intelligences, in all sizes, strengths, and quirks. Discovery, in particular, has always been plural: many curious minds, each devoted to their own question, often on roads less traveled. Our path there is self-improving AI that: -> learns continually on the job, closing the gap between what AI can do off the shelf and what the dynamic world demands -> learns to use other AIs as tools and make new tools to overcome its own limitations -> picks the right-sized model for your problem, at a fraction of the frontier cost Then the power of intelligence, from the craftsmanship of making AI to ownership, can be in the hands of all. @noeri_ai mission reflects who we are as the founding team. My career has been anything but linear, literally continual learning on the job. Carlos has devoted his career to building tools that empower people through AI. We are all a bit contrarian, a bit adventurous, and above all, big believers in pluralism. Join us to build this future together: noeri.ai/

2:17
Chris Barber avatar
⟳ patrick retweeted
Chris Barber@chrisbarber·Nov 15

I asked 56 people in AI which benchmarks they'd trust most to indicate if an LLM is frontier: 25 votes: Terminal-Bench 4 (@alexgshaw, @andykonwinski, @Mike_A_Merrill) 20 votes: Terminal-Bench Science (@StevenDillmann, @lschmidt3, @sanmikoyejo) 13 votes: FrontierCode (@penlume, @ybenpan, @denizbirlikci, @silasalberti) 10 votes: FrontierSWE (@evan_j_chu, @_rajanagarwal, @MatternJustus, @ardnoKhtnayhsiR, @sanket__mhatre, @akshitkr) 8 votes: Humanity's Last Exam (@longphann_, @hendrycks, Alice Gatti, @ziwen_h, @natliml) 7 votes: Vending-Bench (@axelbacklund, @lukaspet) 5 votes each: - AutomationBench (@danielwshepard, @SalimansRobin, @TweetAnnaMarie) - DeepSWE (@winkey_h, @charleyslee, @LeonardMainnet, @serenaa_ge) - PostTrainBench (@full__rank, @hrdkbhatnagar, @AmyPrb, @shiraeis, @karinanguyen, @MatthiasBethge, @maksym_andr) The most common comment was that people don't really trust benchmarks at all. 56 people voted. People couldn't pick a bench their company worked on, an index, or a human-voted board. Disclosure: on this list, I'm a small investor in Abundant, Cognition, Emulated, Fleet, Hillclimb, Latch, and Snorkel. I didn't vote. Counts are net: a few benchmarks received negative votes. Continued:

Post attachment
patrick avatar
patrick@patrickamadeus_·Nov 13

Sora, robotics, whats next? maybe just a short-term business move, or maybe platonic representation hypothesis, scaling law, hardware optimization, distillation, etc. turns out to be the way? thus research should support foundation model maxxing / straight to application layer (agents, enterprises)?

NIK@ns123abcNov 13

🚨 BREAKING: OpenAI has officially disbanded its robotics team, just five months after relaunching it it’s over

Post attachmentPost attachment
patrick avatar
patrick@patrickamadeus_·Nov 13

Day 8 able to write faster today for some reason?

Post attachment

I really wanna be an ambidextrous writer so im doing a 30d challenge (gonna post daily) super chopped but lets see how it goes😭🙏

Post attachment
Xudong Han avatar
⟳ patrick retweeted
Xudong Han@Xudong07452910·Nov 11

之前推荐过几篇 Agent Eval 相关的文章,今天再推荐一篇 LangChain 最新的《What Is Eval-Driven Development》,这篇讲得挺实用,很适合正在做 Agent 和 Harness 的朋友。 文章主要介绍 Eval-Driven Development(EDD),核心思路是把 Eval 融入 Agent 的日常开发。 先定义什么算成功,写好 Eval、跑 Baseline,再修改 Prompt、Tool 或 Harness,通过相同的任务对比效果。 文中有个挺有意思的例子。 给知识库 Agent 新增 create_ticket 工具后,整体 Eval 分数提高了,结果它连「VPN 怎么连接」这种普通咨询都开始创建故障工单。 通过 Trace 排查才发现,工具描述太宽泛,导致 Agent 错误调用了工具。 这也说明不能只看 Eval 平均分。一次改动可能让新任务表现更好,却破坏原本正常的功能。除了最终结果,还需要检查执行轨迹,并保留独立测试集,避免反复优化导致过拟合。 这套思路很值得借鉴,尤其是现在大家都在不断调整 Skill、Prompt 和 Harness。 新增一个 Skill、修改一段 Workflow,甚至删掉旧 Harness,都应该通过 Eval 判断是否真的有效。 感觉 Eval-Driven Development 很值得成为 Agent 开发中的常规习惯,每次迭代都能有据可依。 原文:langchain.com/blog/what-is-e…

vLLM avatar
⟳ patrick retweeted
vLLM@vllm_project·Nov 10

🎉 Great work from the PAN 2 team on an open-weight world model built for real-world simulation, grounded in time, physics and space to predict how scenes evolve as actions unfold. vLLM-Omni brings Day-0 support for PAN 2 text-to-video and image-to-video generation, making it available through an open inference stack.

Introducing PAN 2: an open foundation world model for physical intelligence. A language model predicts the next word. PAN 2 predicts the next world: what happens after each action, grounded in time, physics and space. Towards AI that simulates “what if?” before it acts. More details: ifm.ai/pan/

1:10
patrick avatar
patrick@patrickamadeus_·Nov 10

Bangers as usual Excited to try this on ego2act.github.io !

Introducing PAN 2: an open foundation world model for physical intelligence. A language model predicts the next word. PAN 2 predicts the next world: what happens after each action, grounded in time, physics and space. Towards AI that simulates “what if?” before it acts. More details: ifm.ai/pan/

1:10
Salesforce AI Research avatar
⟳ patrick retweeted
Salesforce AI Research@SFResearch·Nov 9

Interactive Visual Gym: Evaluating Visual Interaction Models Through Simulation Can a visual AI assistant’s real-time advice actually help someone finish a procedural task? Meet Interactive Visual Gym (IVG), an open simulation framework for evaluating and training visual AI assistants in closed loop. We recreate cooking, household, and phone tasks in a simulation world alongside simulated users with different skills and preferences. These users act, make mistakes, ask questions, and respond to guidance – allowing us to test how accurately, appropriately, and promptly an assistant supports them as the activity unfolds. → 14 assistants, 315 scenarios: the best performing model, Gemini-4-Argon, completes only 53.4% of tasks on time → Human preferences match our simulator scores ~80% of the time → Training in the simulator lifts a 4B open model’s success rate’ from 33.3% to 42.2% on unseen tasks Explore the paper, code, and demos: sforce.co/4zwQdWU #EnterpriseAI #AgenticAI #FutureOfAI

2:37
patrick avatar
patrick@patrickamadeus_·Nov 7

Day 6 Its been a busy couple of days, but we back

Post attachment

I really wanna be an ambidextrous writer so im doing a 30d challenge (gonna post daily) super chopped but lets see how it goes😭🙏

Post attachment