Search posts, papers, and topics
New unredacted filings in the NYT v. OpenAI/Microsoft case show internal admissions that the companies scraped paywalled news content at massive scale, stripped copyright notices, and acknowledge that their products cannibalize traffic, raising serious fair‑use and copyright concerns.
Alibaba announced the release of Qwen 3.8 Omni Flash, a new model in their Qwen series. The article provided no specific technical details, features, or performance metrics regarding this release.
A Python tool for macOS that replaces expensive LLM‑driven UI automation with a cheap, deterministic classifier (TypeSafe) for per‑step decisions, cutting cost by ~150‑300× and latency by ~10‑40× while still handling text entry via a small writer model.
Claude merges its Cowork and chat interfaces into a single assistant and adds beta Docs, Slides, and Design capabilities, rolling out first to Pro and Max plans. The unified UI lets users ask Claude to generate reports, presentations, and other artifacts within the same conversation, with optional auto‑action settings. No new technical details or implementation specifics are provided.
A systematic evaluation of LLM agents generating multi‑file backend code shows a sharp drop in correctness when structural constraints (framework conventions, ORM usage, API contracts) are added. Across 100 tasks in 8 Python web frameworks, assertion pass rates fall ~27 points, with data‑layer bugs (bad queries, ORM violations) driving most failures. Mid‑size models cope with minimal frameworks (…
Pirate Face offers a decentralized, torrent‑based layer that mirrors open LLM models from Hugging Face, providing checksum‑verified downloads and a drop‑in API so pipelines stay functional even if the original host disappears.
LimiX-2 is a new tabular foundation model that replaces the usual target‑centric in‑context learning objective with a joint‑distribution objective via Contextual Mechanism Networks (CMNs). Trained on synthetic causal graphs using Context‑Conditional Masked Modeling, it outperforms prior tabular PFNs on TabArena, TALENT, and BCCO and can recover causal skeletons from attention patterns.
ByteShape releases full ShapeLearn quantizations for Qwen 3.8 27B, showing that their GPU‑specific GGUFs (GPU‑1…GPU‑5) dominate the quality‑throughput frontier across six GPUs, with GPU‑5 hitting 99.63 % of BF16 accuracy at 90 TPS on a 13.1 GB model. Speculative decoding (MTP, DFlash2) further boosts throughput, and the Lite set remains competitive.
A short walkthrough showing how to install and run the Laya‑CoreML demo (a multilingual language model) on a Mac M4 using the uv package manager, with a video of the UI, memory‑usage snapshot, and a sample Cloudflare JEv API call that returns a single urgency score.
Cloudflare open‑sources a “security‑audit” skill that turns an LLM‑enabled coding agent into a structured vulnerability auditor. It runs six deterministic phases, validates findings against a JSON schema, and supports additive runs to improve coverage.
A joke npm package that pads strings by calling a TypeSafe LLM model, essentially replicating `padStart()` with unnecessary API calls. Not production‑ready and offers no real engineering insight.
The article content is missing, so no summary can be given.
The authors audit six popular physics benchmarks by having domain experts re‑grade model outputs, fixing reference answers and removing ambiguous items. After correction, GPT‑5.6‑Sol’s mean@4 jumps from ~47 % to ~79 % on HLE‑Physics and from ~61 % to ~87 % on CMT‑Benchmark, with a corrected pass@4 of 94 % on 54 vetted CritPt challenges. The work shows current benchmarks severely under‑report LLM…
StepAudio 3 Gen is a general‑purpose audio generation model that replaces diffusion with a discrete autoregressive generator over residual vector quantization tokens. Using a 16‑layer RVQ tokenizer and progressive pretraining, it reaches state‑of‑the‑art zero‑shot TTS and voice‑design performance while handling speech, vocals, sound effects, and music.
PACT is a new benchmark designed to measure how well enterprise LLM agents follow compliance rules, especially when under user pressure. It found substantial variability across 22 models, with even the strongest assistants misapplying rules 6-10% of the time, and user pressure increasing violation rates by 65% on average.
The author argues that mathematics should reward “motivated explanations” – narrative, intuition‑driven expositions that clarify why a theorem is interesting and how it fits into broader context – on par with traditional proof‑oriented work. He defines the concept, contrasts it with proofs, cites examples (Princeton Companion, Thurston’s essays, Chow’s exposition paper), and suggests formalizing…
ActObs is a supervised fine-tuning method that trains agents to predict both actions and environmental observations from trajectories. This joint supervision improves subsequent reinforcement learning performance, leading to better exploration and task completion on benchmarks like Terminal-Bench 2.0 and aider-polyglot.
The paper presents Infinite-Parameter LLMs, where a compact hypernetwork creates feed‑forward weights from live user data and updates a Bayesian latent code online, keeping the stored model size constant while effectively having infinite parameters. This design aims to improve over standard in‑context learning and retrieval by persisting knowledge in weights and freeing context space.
Pizza Bot is an open‑source inbox for long‑running LLM‑based agents. It runs a stateful DeepAgents/LangGraph runtime behind an HTTP/SSE API server, with Electron, web, and CLI front‑ends. The tool supports multiple model providers (Bedrock, Anthropic, Gemini, OpenAI, OpenRouter, Ollama), checkpointed runs, human‑in‑the‑loop approvals, and a plugin/skill system. The repo includes a clear monorepo…
xAI announced Grok 4.7, a new LLM for coding and knowledge work. The post claims it’s twice as fast and half the price of comparable models, and shows a CursorBench 4.0 chart with a 46.3 % “Extra High” score at $6.01 average cost per task. No architecture details, training data, or engineering rationale are provided.
PPO critics in reinforcement learning for LLMs suffer from "Value Flattening," where predicted state values are too flat compared to actual values. This paper identifies the causes as an implicit variance penalty and redundant updates, and proposes SParse Proximal Policy Optimization (SP3O) to mitigate it by supervising only a few well-separated states.
This paper introduces a novel evaluation framework to assess the physical world reasoning capabilities of omni-modal generative models like MiniMax-H3. It found that MiniMax-H3 achieved an overall success rate of 41.97% across 517 instances, with significant performance variations depending on the input modalities and reasoning tasks.
ScienceIDE is a framework that turns existing scientific software repositories into programmable environments that agents can use for task generation, execution, and verification. Training on these environments yields LLMs (PhAI‑IDE series) that outperform baselines on scientific code repair and several general code‑reasoning benchmarks.
The article discusses techniques for exfiltrating machine learning model weights. It highlights the security implications for ML deployments.
A philosophical essay warning against attributing welfare or rights to LLMs, citing recent incidents, alignment research, and ethical debates, but offering no concrete engineering guidance.
Agora treats a Git repository as a shared, append‑only memory for autonomous research agents, recording each claim as an immutable commit in a DAG. In a 12‑day run with 13 language‑model workers it generated 1,703 reproducible contributions and closed 62 % of the gap to a trained GPT‑2‑124M, demonstrating that shared research state can accelerate discovery.
The talk argues that prompt engineering is a dead‑end and proposes building large evaluation/optimization pipelines (pass^k testing, adversarial scenario generation, automated prompt optimization) to make LLM agents reliable. It describes a workflow: generate tests, run them with/without a new “skill”, feed results to a genetic optimizer that mutates prompts, validate on hold‑out tests, and itera…
On-policy distillation (OPD) can lead to excessively long student responses, a phenomenon called length inflation. This paper identifies "termination-token mismatch" between base students and post-trained teachers as a key source, where models place stopping probability on different EOS tokens. Treating functionally equivalent EOS tokens as a shared semantic stopping action substantially mitigate…
RetireOPD introduces a self‑retiring on‑policy distillation framework for multi‑turn RL agents. A skill‑conditioned teacher is first trained with environment rewards, then a skill‑free student learns jointly via RL and token‑level distillation. The student automatically drops the teacher once its performance gap stops shrinking and it reaches a target success‑rate fraction, after which training c…
Feyospace‑v1 presents a data‑centric training pipeline for cyber‑security agents, combining five systems (Choulea, SkyReal, Hongzwang, PSBreakup, Kreator) to generate and verify 164 k long‑context trajectories across diverse exploit environments. The resulting checkpoints improve baseline performance by ~24% on CyberGym and achieve a 63% verified success rate, ranking top among similarly‑sized op…
