alphaXiv
@askalphaxiv • 58,055 subscribers
High fidelity research
Shorts
Videos
Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability
alphaXiv272,099 次观看 • 3 个月前
arXiv -> quickarXiv Papers are often written in convoluted language that is hard to understand Swap arXiv -> quickarXiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with Z.ai's GLM OCR 🚀 Also includes code + author tweet
alphaXiv74,786 次观看 • 1 个月前
Introducing autoresearch with GPT 5.6 We had GPT 5.6 Sol reproduce the key findings from “Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in LLM Finetuning” Compared to GPT-5.5 and even Fable 5, GPT-5.6 stayed more focused on a few, critical experiments and spent less time on peripheral details. It also asked fewer “clarification” questions and independently resolved ambiguities instead of pushing them back to us OpenAI pushing the boundaries of the automated research loop with models that don’t have handcuffs
alphaXiv88,264 次观看 • 3 个月前
GPT 5.6 Sol can one-shot convert an arXiv paper into an interactive Marimo notebook! Great for papers best understood hands on (lots of fun examples in interpretability, inference engineering, agent harnesses, benchmarking, and more) Play around with the notebook, inspect the code, or try the same workflow with your own agents below
alphaXiv85,661 次观看 • 3 个月前
We are now using Claude Opus 5.5 to create blog-style overviews for every arXiv paper Every claim is backed up with the corresponding evidence highlighted from the paper Generate beautiful research blogs with figures, key insights, and clear explanations with just one click Opus 5.5 features major improvements in writing, perfect for communicating dense research ideas to a broad audience Check it out on any paper on
alphaXiv21,039 次观看 • 25 天前
Introducing autoresearch for GitHub repos Change 'Github' to 'ARGithub' in any repo URL Research artifacts extend beyond papers. Autoresearch is especially useful for experimenting on existing codebases that move fast and outpace their own publications. With one URL change you can now deploy an agent to orient itself on the codebase, resolve setup issues, and iterate on experiments.
alphaXiv73,230 次观看 • 3 个月前
Research papers are filled with citations, but clicking on any of them makes you lose your place in the paper We made citations much easier to navigate, with extra information on hover including authors and institutions Now, you can hover over any in-text citation to instantly preview the referenced paper, jump directly to the full citation, and return to exactly where you left off with a single click This includes quick access to the authors and their organizations, so you can understand the people behind the research without breaking your reading flow Try it now on any paper at
alphaXiv20,712 次观看 • 1 个月前
Introducing LinkedIn for researchers 🚀 LinkedIn optimizes for engagement bait. What about actual research? We aggregated papers, affiliations, experiences, and coauthors to create the most comprehensive profile for every AI researcher You can now ask questions like “Who’s working on automated math discovery at DeepMind?” or "Which researchers are working on world models in San Francisco?" Claim your profile below👇
alphaXiv36,396 次观看 • 2 个月前
