🛠 Tools×75 mentions
Cursor
“Claude 3.5 through Cursor is what I use to assist me in programming.”
Recommended on All-In with Chamath, Jason, Sacks & Friedberg — 2026-05-22
Endorsed by Chamath Palihapitiya, Y Combinator, Y Combinator and 26 others
What the smart people are recommending. 7865 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
“Claude 3.5 through Cursor is what I use to assist me in programming.”
“practical advice on how to get the best out of Claude.”
“cloud code is fant Fantastic. Since quad 4 release, it's become and and ask me again in a few months, I may use something different. But the tools are evolving really rapidly, but I think uh cloud cod…”
“I'm going to show you exactly how I'm using OpenClaw.”
“30% of Fortune 10,000 companies are using Lovable today as well.”
“you will be able to use codex as both your teammate and a competitor so everyone's going to get access to some number of queries to codecs while doing python programming challenges”
“you can go into AI Studio today, for example. You can try the models. You can even fine-tune a model”
“Uhhh... @grok @AskPerplexity this can’t be true, is it?!”
“You can just install Ollama, download DeepSeek, and play with it to your heart's content.”
“I'm going to show you this account that I'm using with cowork. There's no, there's no tasks there because this is sort of like not my burner, but it's my, uh, it's my external account. Uh,”
“Certainly almost all of them are trained with PyTorch. So that's another open source tool produced by by Meta.”
“GitHub co-pilot uh when when when they moved away from the weight lless to the paid version they just thought had like hundreds of thousands of people paying from the first day”
“what do the big AI Labs not understand about companies themselves do you think I think that's such an important question I mean there is just the products being released are just super weird I think t…”
“if you're doing Quantum kkit is the obvious choice”
“I do use Cursor, Windsurf, and some other things.”
“we've seen Devon we've seen Sierra these other these other companies start to emerge um in in the agent space”
“GPT-5.5 is now available on Perplexity for Max subscribers.”
“make sure to go check out AI box.ai if you want to get access to over 80 of the top models in one place for $8.99 a month. Links in the description.”
“Find out more → https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-flash-tts/?utm_source=x&utm_medium=social&utm_campaign=&utm_content=”
“Use those image URLs as reference images or init images in Seedance 2.0 / Seedance 2.0 (Fast)”
“Generate character images with Seedream 5 (Lite) and set return_byteplus_urls=true”
“👉 Signup to LlamaParse to try it out”
“Try it here: https://replicate.com/prunaai/p-video-avatar”
“Benchmarks against Qiskit Aer, QuEST, and Qulacs...”
“Here's DeepSeek v4 Pro. Added to the playable gallery as well.”
“Four days ago, we launched ParseBench, the first document OCR benchmark for AI agents.”
“Q: how do you make diagrams? A: Claude Design - make 5 different SVGs, make a concept and choose one. diagrams, code snippets. use principles of claude design, give design system and references.”
“To install vLLM, follow the directions here”
“Yeah. Yeah. So in total now Jamaa has like all of the YMA based models have over 500 million downloads. Uh but yeah so when we launch new models we want to make sure that people can use the models wit…”
“This short course teaches you to eliminate that waste using SGLang, an open-source inference framework...”
“Seedance 2.0 (Fast): https://replicate.com/bytedance/seedance-2.0-fast”
“I don't know if you've seen the demos of TL draw um it's this it's this yeah it says interface where it's essentially like a blank canvas and you can use prompting to like and drawing to like generate…”
“We provide an accompanying Python package, ppi_aipw, at https://larsvanderlaan.github.io/ppi-aipw/.”
“This paper introduces Memanto, a universal memory layer for agentic artificial intelligence that challenges the prevailing assumption that knowledge graph complexity is necessary to achieve high fidel…”
“These components are enabled by Moorcheh's Information Theoretic Search engine, a no indexing semantic database that provides deterministic retrieval within sub ninety millisecond latency while elimin…”
“We built an end-to-end pipeline that automates it with LlamaParse + the Claude Agent SDK”
“Great to see so many startups building with @googlegemma models!”
“We also develop an open-source library, QGDecoder, enabling the graph-aware bounded distance decoding of arbitrary stabilizer codes.”
“we introduce ATLAS, an annotation tool tailored for long-horizon robotic action segmentation. ATLAS provides time-synchronized visualization of multi-modal robotic data”
“GPT-5.5 and GPT-5.5 Pro are now available in the API.”
“ATLAS reduced the average per-action annotation time by at least 6% compared to ELAN”
“Our experiments on the LibriSpeech corpus show that a larger encoder with a smaller decoder can equal or surpass the performance of architectures with larger decoders.”
“The toolkit is publicly available for research use.”
“✅ Use Canvas in @GeminiApp or @GoogleAIStudio”
“We propose GIST, a training-free, identity-preserving image compositor... Project Page: abhinav-mahajan10.github.io/GIST/.”
“Try the Grok Imagine agent mode beta!”
“and @townai”
“Try Granite 4.1 here 👇 Speech: https://replicate.com/ibm-granite/granite-speech-4.1-2b”
“Try it here 👇”
“Then, take any generated bipedal 3D character and automatically rig it in under 30 seconds with create-character.”
“3D animation and rigging models from @Uthana_Inc are on Replicate!”
“Try text-to-motion v1 and v2: https://replicate.com/uthana/text-to-motion-vqvae-v1”
“Try text-to-motion v1 and v2: https://replicate.com/uthana/text-to-motion-diffusion-v2”
“Council Mode for comparing equity research put out by analysts from different investment banks, now supported on Perplexity Computer”
“codex is also a better slack ai search than slack ai search.”
“Try out Grok STT here: https://replicate.com/xai/grok-speech-to-text”
“Try Granite 4.1 here 👇”
“Try out Grok TTS here: https://replicate.com/xai/grok-text-to-speech”
“In this work, we present SnapLog, an approach to extract event data from videos by converting frames to feature vectors”
“We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing”
“We present failure cases of symbolic evaluation in two popular frameworks, Lighteval and SimpleRL, and compare them to our approach, demonstrating clear improvements over commonly used methods.”
“We present failure cases of symbolic evaluation in two popular frameworks, Lighteval and SimpleRL, and compare them to our approach, demonstrating clear improvements over commonly used methods.”
“Our core technical contribution is the \textbf{DDPO} algorithm,Diversity Driven Policy Optimization, a multi-turn GRPO-based approach designed to preserve dialogue diversity while holistically optimiz…”
“We build upon this promising foundation and extend the method to work as an uncertainty estimation technique for already-trained artificial neural networks in the domain of regression. Our experiments…”
“Based on this observation, we propose QuantClaw, a plug-and-play precision routing plugin that dynamically assigns precision according to task characteristics.”
“We validated our method, QDTraj, by generating diverse trajectories in simulation and deploying them in the real world. QDTraj generates at least 5 times more diverse trajectories for both hinge and s…”
“Overall, H-optimus-1 achieves the strongest survival prediction performance.”
“Notably, the compact distilled model H0-mini slightly outperforms its larger teacher model H-optimus-0, despite using fewer than 8% of the parameters and enabling significantly faster feature extracti…”
“The platform is publicly available at Energy-Arena.org.”
“HDET is implemented as a drop-in replacement for PyTorch's OneCycleLR scheduler, requiring no changes to model architecture, optimizer, or data pipeline.”
“The system uses instruction-tuned qwen3-embedding-0.6B embeddings...Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on a clinical question-answering benchmark.”
“Its closure leaves behind non-updatable benchmarks, irreproducible results, and ultimately a field at risk of perpetuating these issues by turning to closed-source LLMs.”
“OxyGent is publicly available at https://oxygent.jd.com/”
“The resulting corpus comprises ± 35 billion tokens across the medical domain in about 100 million documents, freely available on Hugging Face.”
“the most widely adopted multilingual base (Chatterbox, 23 languages) does not even tokenise Telugu or Tamil”
“the best open-source bases (Chatterbox, Indic Parler-TTS, IndicF5) trail them on measured phonological dimensions”
“For intra-sentential code-mix we add a third branch (IndicF5 + native-script transliteration) that drops code-mix LLM-WER from 0.80-0.85 to 0.14-0.27”
“We release R6 LoRA weights (Apache-2.0), inference code and router (MIT), and a Gradio demo.”
“We introduce Minimum Specification Perturbation (MSP), the smallest number of changes.”
“Our results establish Mollifier Layers as an efficient and scalable tool for physics-constrained learning.”
“Here we introduce PluRel, a framework to synthesize multi-tabular relational databases from scratch.”
“This model and data set combination enables exceptional speed and accuracy for modeling the world at the atomic scale, accelerating the discovery of new molecules and materials.”
“We prove that SOAP, a recently proposed quasi-Newton method, efficiently approximates the Hessian preconditioner, enabling breakthrough performance in PINNs”
“To address these limitations, we introduce Obj-Disco, a framework that automatically decomposes an alignment reward signal into a sparse, weighted combination of human-interpretable natural language o…”
“most people know the Transformers library, but there's a whole ecosystem around it from Diffusers, Sentence Transformers, TRL, PEFT, even LLaVA, and since last week Llama.cpp”
“there's a whole ecosystem around it from Diffusers, Sentence Transformers, TRL, PEFT, even LLaVA, and since last week Llama.cpp. So it's a constellation of tools for AI builders to build with open mod…”
“there's a whole ecosystem around it from Diffusers, Sentence Transformers, TRL, PEFT, even LLaVA, and since last week Llama.cpp. So it's a constellation of tools for AI builders to build with open mod…”
“there's a whole ecosystem around it from Diffusers, Sentence Transformers, TRL, PEFT, even LLaVA, and since last week Llama.cpp. So it's a constellation of tools for AI builders to build with open mod…”
“there's a whole ecosystem around it from Diffusers, Sentence Transformers, TRL, PEFT, even LLaVA, and since last week Llama.cpp. So it's a constellation of tools for AI builders to build with open mod…”
“there's a whole ecosystem around it from Diffusers, Sentence Transformers, TRL, PEFT, even LLaVA, and since last week Llama.cpp. So it's a constellation of tools for AI builders to build with open mod…”
“Meta is the right partner for open-source AI development. Not just with their llama models they have a gamut of other infrastructure llama stack exeutor torch and many libraries.”
“for the AI teammates launched, we have chosen Anthropics Opus 3.6 model. Uh, and that's what we're launching with right now. That's how it's powered. uh it uh did the best in our testing and analysis”
“Connect the dots: Build with built-in and custom MCPs in Studio”
“We introduce MuJoCo Playground, a fully open-source framework for robot learning built with MJX...the entire framework is freely available at playground.mujoco.org”
“we present a systematic taxonomy of jailbreak attacks and defenses and introduce Security Cube, a unified, multi-dimensional framework for comprehensive evaluation of these techniques.”
“Some more vibe-coding fun - every math major's favorite party trick: the wobbly table theorem as an interactive 3D visualization. https://timvieira.github.io/table-theorem/”
“I generate the embeddings locally from PDF or markdown sources using an embedded model @nomic_ai, which supports large docs”
“We present Agent4MR, an agent-based framework that automatically generates and refines PyPulseq sequences using a structured, physics-aware validation report.”
“We evaluated Agent4MR on a spin-echo EPI task across three state-of-the-art LLMs...Agent4MR...automatically generates and refines PyPulseq sequences”
“You can take this even further by connecting Claude Cowork to TradingView using webhooks. When your TradingView strategy triggers an alert, the webhook automatically notifies Claude Cowork, and it exe…”