第31期 | From model to agent: Equipping the Responses API with a...
今日摘要
OpenAI Blog：OpenAI raises $122 billion in new funding to expand frontier AI globally, invest in next-generation compute, and meet growing dema…
X Andrej Karpathy：New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads. Scanning my syst…
OpenAI Blog：Gradient Labs uses GPT-4.1 and GPT-5.4 mini and nano to power AI agents that automate banking support workflows with low latency a…
X Andrej Karpathy：LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of…
OpenAI Blog：OpenAI acquires TBPN to accelerate global conversations around AI and support independent media, expanding dialogue with builders,…
总结 + 观点：Codex now includes pay-as-you-go pricing for Cha…｜中文观点：围绕 Codex now offers more flexible pricing for…
总结 + 观点：AI for Disaster Response in Asia: OpenAI Worksho…｜中文观点：Helping disaster response teams turn AI into…
总结 + 观点：- Drafted a blog post - Used an LLM to meticulou…｜中文观点：- Drafted a blog post - Used an LLM to meticu…
总结 + 观点：Farzapedia, personal wikipedia of Farza, good ex…｜中文观点：比起表面参数，Farzapedia, personal wikipedia of Farz…
总结 + 观点：Something I've been thinking about - I am bullis…｜中文观点：Something I've been thinking about - I am bul…
Accelerating the next phase of AI
标签：#ai_engineering_blogs #core
作者：
原文：OpenAI raises $122 billion in new funding to expand frontier AI globally, invest in next-generation compute, and meet growing demand for ChatGPT, Codex, and enterprise AI.
New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads.
标签：#x_profiles #extended
作者：
原文：New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads. Scanning my system I found a use imported from googleworkspace/cli from a few days ago when I was experimenting with gmail/gcal cli. The installed version (luckily) resolved to an unaffected 1.13.5, but the project dependency is not pinned, meaning that if I did this earlier today the code would have resolved to latest and I'd be pwned. It's possible to personally defend against these to some extent with local settings e.g. release-age constraints, or containers or etc, but I think ultimately the defaults of package management projects (pip, npm etc) have to change so that a single infection (usually luckily fairly temporary in nature due to security scanning) does not spread through users at random and at scale via unpinned dependencies. More comprehensive article: stepsecurity.io/blog/axios-c… Feross (@feross) CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages. The latest axios@1.14.1 now pulls in plain-crypto-js@4.2.1, a package that did not exist before today. This is a live compromise. This is textbook supply chain installer malware. axios has 100M+ weekly downloads. Every npm install pulling the latest version is potentially compromised right now. Socket AI analysis confirms this is malware. plain-crypto-js is an obfuscated dropper/loader that: Deobfuscates embedded payloads and operational strings at runtime Dynamically loads fs, os, and execSync to evade static analysis Executes decoded shell commands Stages and copies payload files into OS temp and Windows ProgramData directories Deletes and renames artifacts post-execution to destroy forensic evidence If you use axios, pin your version immediately and audit your lockfiles. Do not upgrade. https://nitter.net/feross/status/2038807290422370479#m
Gradient Labs gives every bank customer an AI account manager
标签：#ai_engineering_blogs #core
作者：
原文：Gradient Labs uses GPT-4.1 and GPT-5.4 mini and nano to power AI agents that automate banking support workflows with low latency and high reliability.
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research...
标签：#x_profiles #extended
作者：
原文：LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
OpenAI acquires TBPN
标签：#ai_engineering_blogs #core
作者：
原文：OpenAI acquires TBPN to accelerate global conversations around AI and support independent media, expanding dialogue with builders, businesses, and the broader tech community.
Codex now offers more flexible pricing for teams
标签：#ai_engineering_blogs #core
作者：
原文：Codex now includes pay-as-you-go pricing for ChatGPT Business and Enterprise, providing teams a more flexible option to start and scale adoption.
链接：https://openai.com/index/codex-flexible-pricing-for-teams
Helping disaster response teams turn AI into action across Asia
标签：#ai_engineering_blogs #core
作者：
原文：AI for Disaster Response in Asia: OpenAI Workshop with Gates Foundation
链接：https://openai.com/index/helping-disaster-response-teams-asia
- Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing!
标签：#x_profiles #extended
作者：
原文：- Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing! - Fun idea let’s ask it to argue the opposite. - LLM demolishes the entire argument and convinces me that the opposite is in fact true. - lol The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.
Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.
标签：#x_profiles #extended
作者：
原文：Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something: 1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable. 2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information. 3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy. 4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data. So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one. Farza (@FarzaTV) This is Farzapedia. I had an LLM take 2,500 entries from my diary, Apple Notes, and some iMessage convos to create a personal Wikipedia for me. It made 400 detailed articles for my friends, my startups, research areas, and even my favorite animes and their impact on me complete with backlinks. But, this Wiki was not built for me! I built it for my agent! The structure of the wiki files and how it's all backlinked is very easily crawlable by any agent makes it a truly useful knowledge base. I can spin up Claude Code on the wiki and starting at index.md (a catalog of all my articles) the agent does a really good job at drilling into the specific pages on my wiki it needs context on when I have a query. For example, when trying to cook up a new landing page I may ask: "I'm trying to design this landing page for a new idea I have. Please look into the images and films that inspired me recently and give me ideas for new copy and aesthetics". In my diary I kept track of everything from: learnings, people, inspo, interesting links, images. So the agent reads my wiki and pulls up my "Philosophy" articles from notes on a Studio Ghibli documentary, "Competitor" articles with YC companies whose landing pages I screenshotted, and pics of 1970s Beatles merch I saved years ago. And it delivers a great answer. I built a similar system to this a year ago with RAG but it was ass. A knowledge base that lets an agent find what it needs via a file system it actually understands just works better. The most magical thing now is as I add new things to my wiki (articles, images of inspo, meeting notes) the system will likely update 2-3 different articles where it feels that context belongs, or, just creates a new article. It's like this super genius librarian for your brain that's always filing stuff for your perfectly and also let's you easily query the knowledge for tasks useful to you (ex. design, product, writing, etc) and it never gets tired. I might spend next week productizing this, if that's of interest to you DM me tell me your usecase! Video https://nitter.net/FarzaTV/status/2040563939797504467#m
Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of th...
标签：#x_profiles #extended
作者：
原文：Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of their governments. Historically, it is the governments that act to make society legible (e.g. "Seeing like a state" is the common reference), but with AI, society can dramatically improve its ability to do this in reverse. Government accountability has not been constrained by access (the various branches of government publish an enormous amount of data), it has been constrained by intelligence - the ability to process a lot of raw data, combine it with domain expertise and derive insights. As an example, the 4000-page omnibus bill is "transparent" in principle and in a legal sense, but certainly not in a practical sense for most people. There's a lot more like it: laws, spending bills, federal budgets, freedom of information act responses, lobbying disclosures... Only a few highly trained professionals (investigative journalists) could historically process this information. This bottleneck might dissolve - not only are the professionals further empowered, but a lot more people can participate. Some examples to be precise: Detailed accounting of spending and budgets, diff tracking of legislation, individual voting trends w.r.t. stated positions or speeches, lobbying and influence (e.g. graph of lobbyist - firm - client - legislator - committee - vote - regulation), procurement and contracting, regulatory capture warning lights, judicial and legal patterns, campaign finance... Local governments might be even more interesting because the governed population is smaller so there is less national coverage: city council meetings, decisions around zoning, policing, schools, utilities... Certainly, the same tools can easily cut the other way and it's worth being very mindful of that, but I lean optimistic overall that added participation, transparency and accountability will improve democratic, free societies. (the quoted tweet is half-ish related, but inspired me to post some recent thoughts) Harry Rushworth (@Hrushworth) The British Government is a complicated beast. Dozens of departments, hundreds of public bodies, more corporations than one can count... Such is its complexity that there isn't an org chart for it. Well, there wasn't... Introducing ⚙️Machinery of Government⚙️ https://nitter.net/Hrushworth/status/2040406616806179001#m
Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file".
标签：#x_profiles #extended
作者：
原文：Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes builds it for your specific needs. So here's the idea in a gist format: gist.github.com/karpathy/442… You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool. Andrej Karpathy (@karpathy) LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts. https://nitter.net/karpathy/status/2039805659525644595#m
STADLER reshapes knowledge work at a 230-year-old company
标签：#ai_engineering_blogs #core
作者：
原文：Learn how STADLER uses ChatGPT to transform knowledge work, saving time and accelerating productivity across 650 employees.
From model to agent: Equipping the Responses API with a computer environment
标签：#uncategorized #core
作者：
原文：OpenAI engineering 列表显示，Responses API agent computer environment，这意味着模型调用正在往更完整的 agent runtime
链接：https://openai.com/index/equip-responses-api-computer-environment/
Inside our approach to the Model Spec
标签：#uncategorized #core
作者：
原文：OpenAI RSS Model Spec agent
Quantifying infrastructure noise in agentic coding evals
标签：#uncategorized #core
作者：
原文：Anthropic agentic coding benchmark，波动甚至可能超过榜单模型之间的差距。这对 agent eval
链接：https://www.anthropic.com/engineering/infrastructure-noise
Memory Dial: A Training Framework for Controllable Memorization in Language Models
标签：#research_community #extended
作者：
原文：arXiv:2604.05074v1 Announce Type: new Abstract: Memorization in language models is widely studied but remains difficult to isolate and control. Understanding when and what models memorize is essential for explaining their predictions, yet existing approaches are post-hoc: they can detect memorization in trained models, but cannot disentangle its effects from architecture, data, or optimization. We introduce Memory Dial, a training framework that makes memorization pressure an explicit, controllable variable. Memory Dial interpolates between standard cross-entropy and a temperature-sharpened objective via a single parameter $\alpha$, producing a family of models identical in architecture and training setup (within each sweep), differing only in memorization pressure. Experiments across six architectures and five benchmarks demonstrate that: (1) $\alpha$ reliably controls memorization pressure, with seen-example accuracy increasing monotonically while unseen accuracy remains stable; (2) larger models are more responsive to memorization pressure; and (3) frequent sequences are easier to memorize than rare ones. Additional analyses show that the effect is robust across a range of sharpening temperatures, differs qualitatively from single-temperature cross-entropy, transfers to multilingual settings, and is detectable even on naturally occurring single-occurrence sequences. Memory Dial provides a controlled experimental framework for studying how memorization behavior emerges and interacts with generalization in language models.
Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
标签：#research_community #extended
作者：
原文：arXiv:2604.05083v1 Announce Type: new Abstract: While Large Language Models (LLMs) are increasingly adopted as automated judges for evaluating generated text, their outputs are often costly, and highly sensitive to prompt design, language, and aggregation strategies, severely, which limits reproducibility. To address these challenges, we propose \textbf{\textit{OmniScore}}, a family of complementary, deterministic learned metrics developed using small size ($<$1B) parameter models. OmniScore approximates LLM-judge behavior while preserving the low latency and consistency of traditional model-based scoring. We trained the models large-scale synthetic supervision ($\sim$564k instances, in \textbf{107 languages}) and evaluated using 8,617 manually annotated instances. The OmniScore family supports reliable, multi-dimensional scores across a variety of settings, including reference-based, source-grounded, and hybrid evaluations. We evaluate these models across question answering (QA), translation, and summarization in \textbf{6 languages}. Our results demonstrate that lightweight, deterministic learned metrics provide a highly practical and scalable alternative to frontier LLMs. Our models and datasets can be found at https://huggingface.co/collections/QCRI/omniscore
Document Optimization for Black-Box Retrieval via Reinforcement Learning
标签：#research_community #extended
作者：
原文：arXiv:2604.05087v1 Announce Type: new Abstract: Document expansion is a classical technique for improving retrieval quality, and is attractive since it shifts computation offline, avoiding additional query-time processing. However, when applied to modern retrievers, it has been shown to degrade performance, often introducing noise that obfuscates the discriminative signal. We recast document expansion as a document optimization problem: a language model or a vision language model is fine-tuned to transform documents into representations that better align with the expected query distribution under a target retriever, using GRPO with the retriever's ranking improvements as rewards. This approach requires only black-box access to retrieval ranks, and is applicable across single-vector, multi-vector and lexical retrievers. We evaluate our approach on code retrieval and visual document retrieval (VDR) tasks. We find that learned document transformations yield retrieval gains and in many settings enable smaller, more efficient retrievers to outperform larger ones. For example, applying document optimization to OpenAI text-embedding-3-small model improves nDCG5 on code (58.7 to 66.8) and VDR (53.3 to 57.6), even slightly surpassing the 6.5X more expensive OpenAI text-embedding-3-large model (66.3 on code; 57.0 on VDR). When retriever weights are accessible, document optimization is often competitive with fine-tuning, and in most settings their combination performs best, improving Jina-ColBERT-V2 from 55.8 to 63.3 on VDR and from 48.6 to 61.8 on code retrieval.
Multilingual Language Models Encode Script Over Linguistic Structure
标签：#research_community #extended
作者：
原文：arXiv:2604.05090v1 Announce Type: new Abstract: Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal organization remains elusive. In this work, we investigate which linguistic properties - abstract language identity or surface-form cues - shape multilingual representations. Focusing on compact, distilled models where representational trade-offs are explicit, we analyze language-associated units in Llama-3.2-1B and Gemma-2-2B using the Language Activation Probability Entropy (LAPE) metric, and further decompose activations with Sparse Autoencoders. We find that these units are strongly conditioned on orthography: romanization induces near-disjoint representations that align with neither native-script inputs nor English, while word-order shuffling has limited effect on unit identity. Probing shows that typological structure becomes increasingly accessible in deeper layers, while causal interventions indicate that generation is most sensitive to units that are invariant to surface-form perturbations rather than to units identified by typological alignment alone. Overall, our results suggest that multilingual LMs organize representations around surface form, with linguistic abstraction emerging gradually without collapsing into a unified interlingua.
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
标签：#research_community #extended
作者：
原文：arXiv:2604.05091v1 Announce Type: new Abstract: We present MegaTrain, a memory-centric system that efficiently trains 100B+ parameter large language models at full precision on a single GPU. Unlike traditional GPU-centric systems, MegaTrain stores parameters and optimizer states in host memory (CPU memory) and treats GPUs as transient compute engines. For each layer, we stream parameters in and compute gradients out, minimizing persistent device state. To battle the CPU-GPU bandwidth bottleneck, we adopt two key optimizations. 1) We introduce a pipelined double-buffered execution engine that overlaps parameter prefetching, computation, and gradient offloading across multiple CUDA streams, enabling continuous GPU execution. 2) We replace persistent autograd graphs with stateless layer templates, binding weights dynamically as they stream in, eliminating persistent graph metadata while providing flexibility in scheduling. On a single H200 GPU with 1.5TB host memory, MegaTrain reliably trains models up to 120B parameters. It also achieves 1.84$\times$ the training throughput of DeepSpeed ZeRO-3 with CPU offloading when training 14B models. MegaTrain also enables 7B model training with 512k token context on a single GH200.