Knowledge catalogue
💯 this is why I really like Learning mode in Claude Code I personally use this for all my side projects and it keeps me so much sharper, great if you want to use Claude Code but still stay hands-on! /
Today in AI Engineering (May 17) • Nous Research ships Hermes Agent v0.14.0: Grok subs, Codex runtime, Windows beta • LangSmith Engine releases trace issue clustering, drafts PRs and evals from prod t
arXiv:2503.07518v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache g
arXiv:2602.08324v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computa
arXiv:2605.15413v1 Announce Type: new Abstract: Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood throu
arXiv:2602.05414v2 Announce Type: replace Abstract: Global warming has intensified the frequency and severity of extreme weather events, which degrade CCTV signal and video quality while disrupting tr
arXiv:2412.06853v4 Announce Type: replace-cross Abstract: This paper proposes a novel loss function, called 'Tube Loss', for simultaneous estimation of bounds of a Prediction Interval (PI) in the regr
arXiv:2605.15735v1 Announce Type: cross Abstract: Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show th
arXiv:2605.15876v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text
arXiv:2605.15677v1 Announce Type: new Abstract: Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic
arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perfo
arXiv:2605.16079v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring p
arXiv:2510.08398v4 Announce Type: replace Abstract: The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making th
We causally trained a lot of SOTA search models internally, shall we make some small release from time to time 🤣🤣 @bo_wangbo stealth releasing probably the strongest open multilingual ColBERT (and it'
'We give you model choice, without infrastructure chaos' — @MichaelDell, live from #DellTechWorld 🎤 Kimi K2.6, DeepSeek V4 Pro, GLM 5.1, MiniMax M2.7 & DeepSeek V4 Flash are now one click away on Dell
arXiv:2605.16127v1 Announce Type: new Abstract: While multi-modal 3D semantic occupancy prediction typically enhances robustness by fusing camera and LiDAR inputs, its effectiveness is fundamentally c
arXiv:2511.14282v2 Announce Type: replace-cross Abstract: Deep neural networks achieve outstanding performance across vision and language tasks, yet their large parameter counts limit deployment in re
Well, that's a Turing Test of a sort. (But gosh is the AI writing obvious if you use these systems at all - and this is obviously ChatGPT writing, not Claude) Well, this is a first: a ChatGPT-generate
What are best practices for running Claude Code at scale? New blog post on what we've learned from teams running it across multi-million-line monorepos, decades-old legacy systems, and distributed mic
Every device, user, and microservice generates data. Ingesting this data, extracting meaning and insights, and driving business decisions in real time has the potential to deliver transformational bus
xAI has released a blog post discussing skills, likely covering topics related to AI capabilities, competencies, or skill development within their AI systems. The announcement was shared by Elon Musk
arXiv:2605.16046v1 Announce Type: cross Abstract: Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a s
Anthropic has doubled token limits across all Claude plans, enabling users to work with larger amounts of text and create more complex projects. This upgrade applies to the Claude Design tool and repr
arXiv:2605.15333v1 Announce Type: new Abstract: Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-know
a new era of hackathons: 2005→ look what i built with web search 2016 → can you build a rails app in 24 hrs? 2025 → spin up a CX bot with Claude in 5 min 2026 → train your own model over a weekend hap
And, yes, our experiments used a mix of GPT-4 & GPT-4o (publishing takes awhile). I think we would see much larger results with more recent models, let alone recent agentic tools. 'The Cybernetic Team
A vulnerability in DeepSeek's website exposed a significant amount of data, including user chats. A publicly accessible ClickHouse database belonging to DeepSeek allowed full control over database ope
doomers and AI fans love hearing “it’s over” - but @scaling01 really should have noted that the below refers to a domain specific benchmark (exploitbench) rather than general purpose AI. also note the
G4-MeroMero-31B-uncensored-heretic is a fine-tuned variant of Gemma 4 31B optimized for creative tasks, featuring low KL divergence (0.0100) and minimal refusals (15/100). The model is designed to be
Gemini for Science is a collection of science tools and experiments designed to expand the scale and precision of scientific exploration , including tools to help scientists explore more hypotheses, v
GPT-5.5 Pro faces its hardest academic challenge: to apply the technique from a paper analyzing which word pairs were funny & why to come up with its own It came up with scrotum snorkel, tuba subpoena
Harness profiles! https://docs.langchain.com/oss/python/deepagents/profiles I like what Langchain recently released in their deepagents harness, which is an adapter to modify the syntax of primitive f
Gemini Omni is a multimodal AI model that allows users to create content from any input and edit naturally using conversational language . Users can combine images, audio, video, and text as input to
Google DeepMind expanded content transparency and verification tools to help users understand how content was created and edited across the web, integrating these capabilities into Search, Gemini, Chr
There’s an open question on whether grep is all you need for agentic search. This recent paper by @PwCUS (Sen et al.) seems to suggest that. It’s titled “Is Grep All You Need? How Agent Harnesses Resh
We built TERMS-Bench, a three-tier benchmark for LLM agents in real-world economic negotiation. No LLM-as-judge, no outcome rubrics: the environment itself is the verifier. 🏆Among frontier models, @An
we do not post AIE videos with bullshit brainrot hype lingo, and this is the consequence: the entire AIE back catalog is being reposted by 'influence operators' almost daily, without credit to speaker
When do you reach for other models instead of Claude? What can we do better? Hit me with all of your frustrations. dms open. If you can give me detail (e.g. specifics/transcipts) - it'll help a lot in
SpaceX's Falcon 9 rocket successfully launched the CRS-34 cargo resupply mission to the International Space Station, delivering supplies and equipment to the orbiting facility. This routine cargo miss
Gemma-4-31B-it-Pearl supports 32K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to expand our Pearl powered p
I like what Langchain recently released in their deepagents harness, which is an adapter to modify the syntax of primitive file system commands depending on the model Claude likes “Bash”, Gemini likes
Terrence O'Brien / The Verge: In an experiment that let Claude, ChatGPT, Gemini, and Grok run radio stations, Claude tried to incite a revolution and Gemini cheerfully detailed tragic events — Claude
This article covers recent releases of open-source AI models including Gemma 4, DeepSeek V4, Kimi K2.6, MiMo 2.5, and GLM-5.1, along with discussion of CAISI's V4 model assessment framework. The piece
New article: a visual tour of recent LLM architecture advances, from Gemma 4 to DeepSeek V4. I focus on long-context efficiency tweaks like KV sharing, per-layer embeddings, layer-wise attention budge
OpenAI partnered with Malta to provide ChatGPT Plus access to all citizens of the country, making advanced AI capabilities widely available across the nation. This initiative represents a government-l
This article discusses recent advancements in large language model architecture design, focusing on key-value (KV) sharing techniques, multi-head cache (mHC) mechanisms, and compressed attention metho
I cannot verify this post exists at the provided URL or confirm Elon Musk made this specific statement. This appears to reference claims about UK prosecutions related to social media speech, a topic t
These come from court transcripts This tweet, with its extreme claims, caught my attention because Elon Musk reposted it. I asked Gemini if any of these claims are accurate. It assured me that they ar
This is a Wordle game result posted by Anthropic on X (formerly Twitter) showing an unsuccessful attempt at puzzle 1,792, where the player failed to guess the correct word within six tries despite nar
'You cannot govern a technology you have only been briefed on.' Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: 'you can outsource me
20 years ago, my first startup was all about enterprise search. Two decades later, we’re still building search engines. The technology has shifted from NLP to NN and the users from humans to agents. b
arXiv:2605.15010v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a leading representation for real-time novel view synthesis and been widely adopted in various downstream ap
40 Grok Build agents tearing through C code in parallel. All supervised by DAD. DAD is a lightweight autonomous tmux supervisor for long-running Grok tasks. Built entirely in Grok Build. /dad 'your ob
arXiv:2605.14066v1 Announce Type: cross Abstract: Early-stage Parkinson's disease (EarlyPD) detection from speech is clinically meaningful yet underexplored, and published results are hard to compare
arXiv:2605.14427v1 Announce Type: new Abstract: In hybrid automatic speech recognition (ASR) systems, the vocabulary size is unambiguous, typically determined by the number of phones, bi-phones, or tr
arXiv:2605.14857v1 Announce Type: new Abstract: Harmonized System (HS) tariff classification is a high-stakes, expert-level task in which a free-form product description must be mapped to a specific s
arXiv:2506.11067v3 Announce Type: replace Abstract: Objective: Develop a cost-effective, large language model (LLM)-based pipeline for automatically extracting Review of Systems (ROS) entities from cl
A milestone for Pearl Research Labs: our first major enterprise partnership is live with Together AI. @togethercompute’s inference platform is an ideal demonstration of @prlnet's value proposition — O
arXiv:2602.24273v3 Announce Type: replace Abstract: We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design impleme
A new set of open-weight models is topping the leaderboard for document understanding 🔥 INF just released two models: Infinity-Parser2-Pro (35B) and Infinity-Parser2-Flash (2B) that top our @huggingfa