Search: “claude”

arXiv:2610.15722v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are good at video understanding and code generation, but it remains unclear whether they can recover the physic

Scaling code generation without scaling review risks turning coding gains into a larger “review” backlog (whether during PR review or later, when dealing with technical debt, incidents, or bugs). The

Source: whatmodel.sh, an open source AI leaderboard I built (and launched here yesterday). Every point comes from published benchmark results: 22,113 of them across 987 benchmarks, from 1,011 sources,

arXiv:2603.25063v2 Announce Type: replace-cross Abstract: Recent agentic systems demonstrate that large language models can generate complex codebases from natural language prompts. Despite this progr

[UPDATE / RETRACTION: The '100% GTO' claim had a prompt-leakage bug] We patched the repo to pass strictly neutral states, here are the real, honest numbers: • Latency: Still ~2ms (ONNX + Absorbing Mar

I set up a dedicated workstation for local AI experimentation with various models and tools. But every single one of them wants all the available VRAM. To fix this, I built a request dispatching layer

Every few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: shou

I spent a decent amount of time with Gemini 4 before launch. Overall, Gemini 4 is a big jump over previous Gemini models and it is the first non-OpenAI/Anthropic model to pass the Fable/Mythos/Astra b

Lipwise is a [yet another] dictation app for Windows, macOS and Linux. You hold a hotkey, talk, and it types into whatever app has focus but with a twist. Since most of us that speak to our computers

When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside

arXiv:2610.12789v1 Announce Type: new Abstract: Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa

I've made a few posts recently, just talking about the hardware I've got and the model I use. Pair of P100s, Unsloth Qwen3.6 35b A3B UD Q4 K XL. There's been a ton of talk of model and hardware specif

arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demon

arXiv:2610.12954v1 Announce Type: new Abstract: This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted r

New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,

arXiv:2610.13563v1 Announce Type: cross Abstract: Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests,

arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg

Here're results from my final test of coding, coding (panda/numpy), data analysis, data-driven decision-making, and local RAG domains I interact with most often. This test, which is refined from a 500

arXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue tha

Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Agent You can find it in the optional built in skills in the sk

It's been 4 years since c.ai first hallucination model, and yet, we're nowhere good enough at LLMs in terms of spontaneity/interesting hallucination features. Fortunately, last year brought new archit

Alright, I learend a few valuable lessons since I posted about a week ago, and I've made more strides with the DDR4x Ascend 96GB 310P cards I purchased, so here we go, meet the new friendly and less v

We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud

https://preview.redd.it/9k5fw4j47puh1.png?width=545&format=png&auto=webp&s=ff0a6ff6fb69ae9a9bcd579bd612c553fc3e2a00 https://preview.redd.it/xcwzlmo77puh1.png?width=664&format=png&auto=webp&s=c8a637e2e

Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27B open model beats the strongest open autoresearch baseline

I ran a small test for Dory to see whether a local model could update one fact in a synthetic notes file without losing any of the others. I asked Gemma and Qwen to rewrite the file, return a patch, o

arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-

arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c

Banger paper from Meta Superintelligence Labs on user simulators for agent training. Agent RL setups usually let an assistant LLM play the user, so the simulated user is too cooperative and too explic

arXiv:2610.12341v1 Announce Type: new Abstract: Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain

arXiv:2610.11542v1 Announce Type: cross Abstract: Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden

arXiv:2610.10961v1 Announce Type: cross Abstract: Coding agents increasingly share a workstation while drawing on separate providers and subscription allowances. A second agent can inspect a completed

arXiv:2610.11402v1 Announce Type: new Abstract: GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making p

Last month I created a portable memory format as a .txt file as a small project. I named it as: Memory Journal, in a shape of a skill card. It's essentially a large prompt wrapped in a text file. Init

arXiv:2610.09484v2 Announce Type: replace Abstract: Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and diffic

arXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intell

arXiv:2610.11233v1 Announce Type: cross Abstract: A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion. Existing approaches ei

Referring to specifically Unsloth's UD_Q4_K_XL quant because that's going to be a question, and is relevant regardless. It's old now. It's not great at coding medium sized or even small-ish projects.

(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next

arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic ben

Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel

I've been building ANCHOR, a web automation agent that runs entirely on Ollama. You describe a task in plain language ('Register Maria Silva, IT department, contractor, and save'), point it at a site,

arXiv:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for

arXiv:2610.11008v1 Announce Type: cross Abstract: Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decis

arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges tak