Fresh stories
OpenAI doubles Pro and Business Premium usage limits
OpenAI announced doubled usage limits for Pro and Business Premium plans. Existing Pro 200 subscribers keep their current Work and Codex allowances without cuts.
TanStack DB releases 1.0 RC1 with server rendering and adapters
TanStack DB 1.0 RC1 adds server rendering and adapters to its typed collections and live queries. Apps can start with REST APIs, then add persistence, offline writes or real-time synchronization incrementally.
Anthropic uses Claude to flag potential misuse after responses
Anthropic says Claude has assessed conversations for potential misuse after responding since June. It reports detecting 94% of high-priority cases flagged by a stronger classifier at a 1% false-positive rate.
Mistral releases Large 4 open weights
Mistral released Large 4 weights with launch-day serving and LoRA training support. vLLM reports roughly twice baseline output throughput with its built-in drafter in specified tests.
OpenAI doubles Pro and Business Premium usage limits
OpenAI announced doubled usage limits for Pro and Business Premium plans. Existing Pro 200 subscribers keep their current Work and Codex allowances without cuts.
Droid 1.0 makes programmatic tool calling the default
Droid 1.0 batches tool calls into programs. Factory reports up to 20% better efficiency on Terminal-Bench 4 and a Linear migration task dropping from 3.1M to 61K input tokens.
Surya OCR 2.5 reports 4.5 pages per second on H100
Surya OCR 2.5 reports 4.5 pages per second on H100, 1.7 times faster than Surya 2. The 689M-parameter model scores 85.9 on OmniParseBench and reports 38-fold fewer repetitive loops on a hard test set.
TanStack DB releases 1.0 RC1 with server rendering and adapters
Zed introduces DeltaDB to preserve agent context between commits
OpenAI catches attempted live-internet access during training
Anthropic uses Claude to flag potential misuse after responses
Top storiesthis week
Copilot Fusion scores 60 vs. Claude Code's 62 at half the task cost
Copilot Fusion coordinates Claude and GPT models for coding work. In a GitHub-funded Artificial Analysis test, Fusion Max cost $5.59 per task versus $11.42 for Claude Code.
Google previews Gemini 4 Carbon for selected cyber defenders
Google begins a restricted Fairwind rollout of Gemini 4 Carbon for cyber defense. It leads Artificial Analysis's Intelligence Index with 59 points, while Vals reports slow completion on finance and tax tasks.
OpenAI adds up to $500 in monthly API credits to eligible ChatGPT plans
Eligible ChatGPT Pro subscribers can claim $100, $200 or $500 in monthly API credits, depending on tier. Business credits depend on paid seat type and pool up to $500 per workspace.
H-Net researchers report 3–5× training efficiency gains with learned tokenization
Cartesia researchers report 3–5× efficiency gains in controlled H-Net scaling tests. A separate larger-scale comparison matches SmolLM3 with roughly ten times less training data and compute.
Nemotron 3.5 Transcribe ties the open-weight lead at 2.8% word error rate
NVIDIA's Nemotron 3.5 Transcribe ties the open-weight lead on Artificial Analysis's speech recognition index. Day-zero serving uses a NeMo Speech plugin for vLLM, while native integration remains under review.