
Cursor Traces Malicious Claude Code Extension to Third-Party Breach
A compromised key issued to AI infrastructure provider Fireworks was used by threat actors to access Cursor data and credentials.

A compromised key issued to AI infrastructure provider Fireworks was used by threat actors to access Cursor data and credentials.

The frontier model races continues. A week after the launch of Anthropic’s Claude 5.2 and Google’s Gemini 4 Hydrogen, OpenAI is releasing GPT-6.2 Astra and Sol as a “new standard for professional work.”

Proton's new Lumo Desktop app for Windows, Mac, and Linux lets users automate tasks across files and connected apps, with granular controls over what its AI can access.

Atli launched an MCP connector for buying and managing travel eSIMs through AI assistants, covering more than 200 countries.

Anthropic’s AI bot Claude is close on the heels of Indian AI market leader ChatGPT, with the former’s adoption outpacing…

Velocity said Vector uses the Model Context Protocol, introduced by Anthropic, to connect shipping workflows with AI apps such as Claude and ChatGPT.
A vision-language model (VLM) can judge 3-D relations from the picture or from the ground layout. In photographs the two usually agree. We separate them with CueClash, rendered scenes in which the 2-D cue for each of five relations is right on exactly half the statements. The shortcut gap is accuracy when the cue is right minus accuracy when it is wrong. For Claude Opus 5.5, GPT-5.5 and Gemini 3.6 Flash at low reasoning effort it is +18 to +37 percentage points. It is +7 to…

Claude can now embed text, buttons, and other web elements into complex graphics and 3D effects. The article Claude now builds interactive websites inside canvas graphics, reviving the Flash era with real HTML appeared first on The Decoder.

The attacker stole an access key from Fireworks and used it to exfiltrate credentials that enabled them to push malicious Claude Code extension copies.

Anthropic studied how Claude retains knowledge across sessions. Selective notes beat exhaustive archives by a wide margin. In a Pokémon Red test, the newer Claude Fable 5 got four times as far as the older Sonnet 3.7 by keeping just a handful of strategy files instead of more than 400. A "Dreaming" process retroactively corrects faulty memories. The article Anthropic says the key to agent memory is knowing what to forget, not how much to store appeared first on The Decoder.

Alibaba's Qwen4-Max costs $1.50/$4.50 per million tokens, cuts task costs by 62%, and was trained to avoid offensive hacking skills.
Venues and benchmarks read LLM review scores as measurements of a paper, while providers replace their models within months. We audit twenty frontier models from OpenAI, Google and Anthropic on ICLR 2027 submissions while they were under review, with tests registered before the decisions. Between an earlier and a later version of Claude Opus and of Gemini, the share of papers placed on the accept side falls by 52 and 53 percentage points on 183 and 60 randomly drawn…
Weight-space programming allows a language model to edit another model's weights without gradient-based training. We used Claude Opus 5.5 to edit Qwen3.5-0.8B and investigated how the edits changed its use of Python on computational biology problems. We compared four initial edited checkpoints with the original model on 50 test problems across three test seeds, yielding 600 paired evaluations. Strictly correct answers increased from 44 to 77, and technically correct answers…

Release: datasette-maplibre 0.1a0 The first new Datasette geospatial plugin in quite a while! This one combines the excellent MapLibre GL library with OpenFreeMap, the free vector map server operated by Zsolt Ero (you should sponsor Zsolt on GitHub.) I built most of this with a single prompt to Claude Fable 5.2: Look at datasette-cluster-map and datasette-leaflet-geojson plugins, then look at ~/dev/tools/openfreemap-demo.html - then build a brand new Datasette plugin that…
Release: datasette 1.0a43 I've been leaning hard into Claude Fable 5.2 to help knock things off the 1.0 milestone, which is now 53% complete. The biggest 1.0 item in this release is streaming support for output renderers - the built-in TSV and CSV export mechanisms now use this as well, and plugins can register themselves as capable of streaming every row in a table in one go via the new Response.stream() method. There are a couple of security fixes, one of which I deemed…

Anthropic's Claude Fable 5.2 doesn't generate images the way other AI models do. Instead of computing pixels, the language model writes Python code that places hundreds of thousands of simulated brushstrokes on a virtual canvas, complete with bristle texture and paint application. A single photorealistic parking garage scene took roughly 700,000 strokes, according to Anthropic employee Jake Eaton. The article Anthropic's Claude Fable 5.2 doesn't generate images, it paints…

Anthropic released Claude Fable 5.2 on November 9 and said it beats Claude Opus 5.5 in almost every capability the

Meituan has released the weights for LongCat-2.5, a 1.6-trillion-parameter model built for AI agents and trained entirely on Chinese hardware. On Terminal Bench, it scores 88.4 points, landing just behind Claude Opus 5. The sample deployment runs on 194 Huawei Ascend chips, and Meituan makes no mention of Nvidia GPUs. The article Meituan releases a 1.6-trillion-parameter agent model that never touched an Nvidia GPU appeared first on The Decoder.

Here’s an overview of some of last week’s most interesting news, articles, interviews and videos: What a security leader should tell the CEO about leaked credentials In this Help Net Security interview, Eric Fourrier, CEO of GitGuardian, talks about leaked credentials and personal liability for security leaders and boards. He explains how fear of blame pushes mistakes out of sight, and what a security leader should be ready to tell a CEO about exposed keys. … More →

The compromise of Anthropic's official Claude Code extension on Cursor's extension marketplace was the result of the theft of an access key that was exposed in the wake of a breach targeting Fireworks AI. "An attacker obtained an access key we had issued to Fireworks," Cursor said in a Friday update. "The key was exposed by Fireworks, and the attacker used it to copy data from a read-only
Release: datasette-apps 0.4a0 Datasette Apps are sandboxed HTML and JavaScript applications that live inside Datasette - think Claude Artifacts, but these ones can run SQL queries against your data. 0.4a0 adds support for linking: you can link to an app with #fragments in the URL and the app can see and use those, plus supported URL schemes are reported back to Datasette Agent so it can help write apps that link to each other. This means you can have e.g. an app that shows…

Anthropic’s Claude Fable 5.2 promises fewer refusals and lower token prices, but those changes played out very differently in our

Anthropic has made Claude Opus 5.5 the default model on all paid plans and published a guide that does away with old prompting habits. The main takeaway is to drop "think hard" and start at Medium effort. The article Anthropic says outdated prompting habits are slowing down Claude Opus 5.5 appeared first on The Decoder.

Anthropic wants developers to build businesses on Claude, but its expansion into enterprise software is raising concerns among founders that

Anthropic is positioning its new model, Claude Fable 5.2, for demanding coding and technical work. Anthropic launched Fable 5.2 on

Anthropic has unveiled a self-hosted version of its platform for building and running AI agents. Self-hosted Claude Managed Agents, as
Robot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5.2, whereas open-weight models remain substantially less capable. We show that an open-weight 27B reasoning model can be trained to use real robots natively through reinforcement learning, entirely in simulation and without demonstrations. Like a…
Autonomous trading agents need controls that prevent problematic orders without making legitimate tasks impractical. We study this aspect of agentic compliance with TradeGauntlet, a replayable limit-order-book simulator that separates detection, prevention, and execution cost. In 1,680 simulated sessions with Claude Haiku 5.5 and Sonnet 5.5, all conduct alerts were self-matches. Gates eliminated those alerts by rejecting self-crossing orders, while the aggregate-gate…

Anthropic's new Claude for Manufacturing plugin connects the AI directly to Autodesk Fusion, Oracle NetSuite, and Infor. Its 17 specialized skills let the AI draft quotes, compare suppliers, and place backup orders when deliveries are delayed, all after human approval. The plugin doesn't control physical machines yet, but Anthropic is separately developing the Model Hardware Standard for that. The article Anthropic's Claude for Manufacturing plugs AI directly into factory…

It not just you, Claude is down.