第14期 | Extreme Harness Engineering for Token Billionaires: 1M L...
今日摘要
X Andrej Karpathy：The signature is alluding to NVIDIA GTC 2015, where Jensen excitedly told an audience of, at the time, mostly gamers and scientifi…
X Andrej Karpathy：Thank you Sarah, my pleasure to come on the pod! And happy to do some more Q&A in the replies. sarah guo (@saranormous) Caught up…
X Andrej Karpathy：Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure c…
X Andrej Karpathy：(I cycle through all LLMs over time and all of them seem to do this so it's not any particular implementation but something deeper…
X Andrej Karpathy：One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 m…
总结 + 观点：OpenAI launches a Safety Bug Bounty program to i…｜中文观点：从 Introducing the OpenAI Safety Bug Bounty pr…
总结 + 观点：When I built menugen ~1 year ago, I observed tha…｜中文观点：从 When I built menugen ~1 year ago, I observe…
总结 + 观点：Learn how STADLER uses ChatGPT to transform know…｜中文观点：围绕 STADLER reshapes knowledge work at a 230-y…
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：AI for Disaster Response in Asia: OpenAI Worksho…｜中文观点：Helping disaster response teams turn AI into…
The signature is alluding to NVIDIA GTC 2015, where Jensen excitedly told an audience of, at the time, mostly gamers and scientific computin...
标签：#x_profiles #extended
作者：
原文：The signature is alluding to NVIDIA GTC 2015, where Jensen excitedly told an audience of, at the time, mostly gamers and scientific computing professionals that Deep Learning is The Next Big Thing, citing among other examples my PhD thesis (one of the first image captioning systems that coupled image recognition ConvNet to an autoregressive RNN language model, trained end to end). This was back when most people were still unaware and somewhat skeptical but of course - Jensen was 1000% correct, highly prescient and locked in very early.
Thank you Sarah, my pleasure to come on the pod! And happy to do some more Q&A in the replies.
标签：#x_profiles #extended
作者：
原文：Thank you Sarah, my pleasure to come on the pod! And happy to do some more Q&A in the replies. sarah guo (@saranormous) Caught up with @karpathy for a new @NoPriorsPod on the phase shift in engineering, AI psychosis, claws, AutoResearch, the opportunity for a SETI-at-Home like movement in AI, the model landscape, and second order effects 02:55 - What Capability Limits Remain? 06:15 - What Mastery of Coding Agents Looks Like 11:16 - Second Order Effects of Coding Agents 15:51 - Why AutoResearch 22:45 - Relevant Skills in the AI Era 28:25 - Model Speciation 32:30 - Collaboration Surfaces for Humans and AI 37:28 - Analysis of Jobs Market Data 48:25 - Open vs. Closed Source Models 53:51 - Autonomous Robotics and Atoms 1:00:59 - MicroGPT and Agentic Education 1:05:40 - End Thoughts Video https://nitter.net/saranormous/status/2035080458304987603#m
Software horror: litellm PyPI supply chain attack.
标签：#x_profiles #extended
作者：
原文：Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords. LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm. Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks. Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages. Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible. Daniel Hnyk (@hnykda) LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server self-replicate. link below https://nitter.net/hnykda/status/2036414330267193815#m
(I cycle through all LLMs over time and all of them seem to do this so it's not any particular implementation but something deeper, e.g.
标签：#x_profiles #extended
作者：
原文：(I cycle through all LLMs over time and all of them seem to do this so it's not any particular implementation but something deeper, e.g. maybe during training, a lot of the information in the context window is relevant to the task, so the LLMs develop a bias to use what is given, then at test time overfit to anything that happens to RAG its way there via a memory feature
One common issue with personalization in all LLMs is how distracting memory seems to be for the models.
标签：#x_profiles #extended
作者：
原文：One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity. Some kind of trying too hard.
Introducing the OpenAI Safety Bug Bounty program
标签：#ai_engineering_blogs #core
作者：
原文：OpenAI launches a Safety Bug Bounty program to identify AI abuse and safety risks, including agentic vulnerabilities, prompt injection, and data exfiltration.
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have...
标签：#x_profiles #extended
作者：
原文：When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction! Patrick Collison (@patrickc) When @karpathy built MenuGen karpathy.bearblog.dev/vibe-c… he said: "Vibe coding menugen was exhilarating and fun escapade as a local demo, but a bit of a painful slog as a deployed, real app. Building a modern app is a bit like assembling IKEA future. There are all these services, docs, API keys, configurations, dev/prod deployments, team and security features, rate limits, pricing tiers." We've all run into this issue when building with agents: you have to scurry off to establish accounts, clicking things in the browser as though it's the antediluvian days of 2023, in order to unblock its superintelligent progress. So we decided to build Stripe Projects to help agents instantly provision services from the CLI. For example, simply run: stripe projects add posthog/analytics And it'll create a PostHog account, get an API key, and (as needed) set up billing. Projects is launching today as a developer preview. You can register for access (we'll make it available to everyone soon) at projects.dev We're also rolling out support for many new providers over the coming weeks. (Get in touch if you'd like to make your service available.) projects.dev https://nitter.net/patrickc/status/2037190688950161709#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.
- 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.
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
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.
Show HN: Gemma 4 Multimodal Fine-Tuner for Apple Silicon
标签：#research_community #core
作者：
原文：About six months ago, I started working on a project to fine-tune Whisper locally on my M2 Ultra Mac Studio with a limited compute budget. I got into it. The problem I had at the time was I had 15,000 hours of audio data in Google Cloud Storage, and there was no way I could fit all the audio onto my local machine, so I built a system to stream data from my GCS to my machine during training. Gemma 3n came out, so I added that. Kinda went nuts, tbh. Then I put it on the shelf. When Gemma 4 came out a few days ago, I dusted it off, cleaned it up, broke out the Gemma part from the Whisper fine-tuning and added support for Gemma 4. I'm presenting it for you here today to play with, fork and improve upon. One thing I have learned so far: It's very easy to OOM when you fine-tune on longer sequences! My local Mac Studio has 64GB RAM, so I run out of memory constantly. Anywho, given how much interest there is in Gemma 4, and frankly, the fact that you can't really do audio fine-tuning with MLX, that's really the reason this exists (in addition to my personal interest). I would have preferred to use MLX and not have had to make this, but here we are. Welcome to my little side quest. And so I made this. I hope you have as much fun using it as I had fun making it. -Matt Comments URL: https://news.ycombinator.com/item?id=47680309 Points: 158 Comments: 22
System Card: Claude Mythos Preview [pdf]
标签：#research_community #core
作者：
原文：Related: Project Glasswing: Securing critical software for the AI era - https://news.ycombinator.com/item?id=47679121 Assessing Claude Mythos Preview's cybersecurity capabilities - https://news.ycombinator.com/item?id=47679155 Comments URL: https://news.ycombinator.com/item?id=47679258 Points: 637 Comments: 450
链接：https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf
Extreme Harness Engineering for Token Billionaires: 1M LOC, 1B toks/day, 0% human code, 0% human review Ryan Lopopolo, OpenAI Frontier Symph...
标签：#ai_engineering_blogs #core
作者：
原文：We shed light on OpenAI's first Dark Factory for the first time.
Deep Agents v0.5
标签：#ai_engineering_blogs #core
作者：
原文：TL;DR: We've released new minor versions of deepagents deepagentsjs featuring async (non-blocking) subagents, expanded multi-modal filesystem support, and more. See the changelog for details. Async subagents Deep Agents can now delegate work to remote agents that run in the background. As opposed to the existing
Building real-time conversational podcasts with Amazon Nova 2 Sonic
标签：#engineering_ai_infra_blogs #extended
作者：
原文：This post walks through building an automated podcast generator that creates engaging conversations between two AI hosts on any topic, demonstrating the streaming capabilities of Nova Sonic, stage-aware content filtering, and real-time audio generation.