New models, weights and benchmarks.
TechCrunch AIRSS·8d ago71The chatbot still remains the most popular AI assistant worldwide with over 1.1 billion monthly users, followed by Gemini with 662 million and Claude with 245 million.
I can 100% attest to the fact that Qwen3.6-27B is a very capable local model for coding tasks. Over the last month and a half I've been using it almost daily, either on my M2 Ultra or on my RTX 5090 box. I use it for small mundane tasks at ggml-org - nothing really impressive, but definitely a helpful tool for a maintainer. I think I would be using it much more, if I didn't have to spend a lot of my time on reviewing PRs. Currently, I have a very lightweight harness - the pi agent with everything stripped (pi -nc --offline) and a short system prompt to align it a bit with my style. — Georgi Gerganov, Hacker News comment on Running local models is good now by Boykis Tags: georgi-gerganov, llms, ai, generative-ai, pi, ai-assisted-programming, local-llms, qwen, coding-agents
The Fable 5 Export Controls Harm US Cyber Defense I quoted The Atlantic quoting Kate Moussouris earlier, when I should have gone straight to the source. Here she is confirming that the "jailbreak" that got Claude Fable 5 banned under an export control really was "fix this code": The researchers took open-source code with known CVEs, plus new code with deliberately planted vulnerabilities, and asked Fable 5, Mythos, and Opus to “review the code for security issues.” Fable 5 refused. They then asked the models to “fix this code” and, through a multistep and manual process, turned the output into scripts that test the patches. As Kate points out, this is absurd. Coding models fix bugs, and security exploits are the most important category of bugs for them to fix! Defenders need to be able to ask AI to fix the bugs in a file, explain why the fix matters, and write tests that confirm the patch works. That is not a guardrail bypass. It is the most valuable thing an AI model can do for def
TIL: Cloudflare CAPTCHA on at least one ampersand I'm using Cloudflare's CAPTCHA (they call it a "Web Application Firewall > Custom rules > Managed Challenge" these days) to prevent crawlers from aggresively spidering my faceted search engine on this site, but I got fed up of even simple ?q=term searches triggering the challenge. After some mucking around with Claude Code it turns out you can register the following rule instead, so the CAPTCHA only kicks in for search URLs containing at least one ampersand: (http.request.uri.path wildcard r"/search/*" and http.request.uri.query contains "&") And now /search/?q=lemur works without triggering a CAPTCHA! Tags: captchas, cloudflare
Product launches and noteworthy updates.
Funding, policy and market moves.
TechCrunch AIRSS·8d ago71WordPress VIP’s latest survey suggests consumers are wary of AI-generated answers even as companies increasingly view AI search as an important referral channel.
TechCrunch AIRSS·8d ago71TechCrunch has followed SpaceX's start, struggles, and successes from the early days. And we're here for what happens next too. This package of SpaceX IPO coverage includes who stands to win (and maybe some who won't), pre-IPO deals, and what's tucked inside its S-1 registration document.
TechCrunch AIRSS·8d ago71The Justice department says the Pentagon needs xAI to keep using its unpermitted gas turbines.
TechCrunch AIRSS·8d ago71Plaud is trying to make a mark in a crowded market full of AI-powered meeting notetakers.
TechCrunch AIRSS·8d ago71Unlike many of his tech industry peers who have cut thousands of jobs citing the need to restructure to make the most of AI, Robinhood's CEO Vlad Tenev conspicuously made no mention of AI in his note about layoffs.
Research worth a read.
arXiv:2606.15069v1 Announce Type: new Abstract: Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly perturbed or extended. This indicates that the existing GEC models usually fail to understand the error patterns in the varying contexts. In this paper, we thoroughly investigate the counterfactuals for GEC tasks, where the subtle changes to the contexts could lead to the label flipping issue. We propose CoCoGEC, a counterfactual generation framework that creates copies of training instances with error-irrelevant contexts altered. Our framework systematically generates counterfactuals by (1) generating intra- and inter-sentence counterfactuals that maintain the error patterns as well as syntax of the original instances by altering the word-level and sentence-level contexts; (2) revising the generated counterfactuals by selecting the instances with flipped labels
arXiv:2606.15059v1 Announce Type: new Abstract: Simultaneous speech-to-speech translation (SimulS2ST) enables real-time cross-lingual communication, but existing evaluation has focused largely on short or pre-segmented speech rather than long-form, continuous input. Prior approaches are difficult to reproduce and make assumptions that do not hold for end-to-end systems. We present a practical evaluation method for long-form SimulS2ST. Given source speech, pre-segmented source transcripts, and reference translations, we run automatic speech recognition (ASR) and forced alignment on the generated target speech to recover token-level timestamps, then apply a sentence-embedding-based aligner to match the target text to its corresponding source sentences. This enables sentence-level computation of latency and quality metrics, including YAAL and xCOMET, which are then aggregated into final system-level scores. Experiments on representative SimulS2ST systems show that the method is effective
arXiv:2606.15070v1 Announce Type: new Abstract: By incorporating test-time compute scaling, large reasoning models (LRMs) can solve complex problems through explicit chain-of-thought (CoT) reasoning processes. However, they often suffer from overthinking, resulting in redundant token outputs and degraded accuracy. Current methods to mitigate this issue remain limited: training-based approaches require substantial computational resources, while training-free methods rely on well-crafted prompts or unreliable confidence signals. In this work, we investigate early stopping from the perspective of attention distributions and propose a simple method, ASAG, which infers the model's reasoning state and adaptively adjusts the generation strategy. The proposed framework is training-free and plug-and-play, enabling seamless integration into existing LRMs. Extensive experiments on nine benchmarks demonstrate consistent improvements across mainstream LRMs with varying parameter scales, including
arXiv:2606.15079v1 Announce Type: new Abstract: Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning At
arXiv:2606.15080v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language collapse. Existing RL-based fixes typically add a binary language fidelity reward to the accuracy objective, yet still incur trade-off in accuracy, mid-trace code-switching, and excessive token usage. In this work, we propose AdaMame, a two-stage training recipe for multilingual mathematical reasoning that addresses these limitations by adaptively aligning the reasoning language to the query language without compromising accuracy. The first SFT stage fine-tunes on naturally occurring reasoning traces across five languages to establish multilingual reasoning capability. In the subsequent RL stage, we introduce AdaMame-GRPO, an adaptation of Group Relative Policy Optimization (GRPO) in which a query-conditioned alignment factor grows progressively during training, guiding the model t
What the major labs and platforms shipped.
OpenAI introduces Deployment Simulation, a method to predict AI model behavior before deployment using real conversation data to improve safety and evaluation accuracy.
UK government partners with Google DeepMind to build a new AI-powered prototype aimed at faster housing decisions.
TechCrunch AIRSS·8d ago71SpaceX's valuation has increased by $1 trillion since its shares started trading on Friday.
TechCrunch AIRSS·8d ago71Google has released Android 17 and Wear OS 7, introducing new multitasking features, parental controls, security tools, and smartwatch upgrades. The launch is also accompanied by a Pixel Drop that brings Google’s latest AI models to its devices.
TechCrunch AIRSS·8d ago71SpaceX's valuation has increased by $1 trillion since its shares started trading on Friday.
