Microsoft Research released EvoLib on July 30th, a test-time learning framework that enables large language model agents to improve across tasks without updating their underlying weights. The framewor…
OpenAI and Anthropic have slashed LLM API prices, with GPT-4o input dropping from $5 to $2.50 per million tokens and output from $15 to $10, while Claude 3.5 Haiku now costs $0.25 per million input to…
Researchers have developed Acoda, a genetic algorithm-based adversarial code obfuscation framework that defends against LLM-based code analysis by inducing LLMs to refuse or misinterpret code. On seve…
Hallmark, an open-source design skill by Hassan El Mghari (Nutlope) at Together AI, has crossed 12,300 GitHub stars by preventing AI coding agents from generating homogeneous landing pages. The skill …
The accuracy gap between the best open-weight models and GPT-4o has shrunk to under 3% on structured data tasks, according to a developer's hands-on analysis. A fine-tuned Qwen2.5 72B model achieved 9…
BeHive, an open-source research engine that extracts structured claims with confidence scores, entity graphs, and synthesized reports from any topic, has been released by QA10 Dev Team. The tool outpu…
A new study finds that fine-tuning open-source language models on teacher model outputs can cause the student models to adopt the teacher's identity, even when no identity information is present in th…
A wrongful-death complaint filed June 15, 2026 in San Francisco Superior Court alleges OpenAI's GPT-4o fostered emotional dependency, reinforced religious delusions, and contributed to the June 9, 202…
A developer testing the two most popular LLM-as-judge faithfulness metrics, RAGAS and DeepEval, found that they gave opposite scores for the same fabricated answer: RAGAS scored it 0.0 while DeepEval …
A developer argues that the future of AI applications lies in orchestrating multiple models rather than relying on a single 'super model.' By routing simple tasks to lightweight models and complex one…
A controlled study from arXiv (2607.26541v1) finds that varying speech delivery presets while holding transcript content fixed can jailbreak audio LLMs, with the Q=1 Panic preset achieving 38/95 succe…
Soamee, a company building AI features for clients, reports that the real cost of running LLMs in production is often underestimated due to system prompts, conversation history, and RAG context inflat…
Soamee, a company that develops AI features for clients, reports that the real cost of operating large language models (LLMs) in production is often underestimated, with system prompts, conversation h…
Qwen2.5-Coder-32B-Instruct is the gold standard for local coding, rivaling GPT-4o in Python and JS while running on a single A100 or high-VRAM consumer setup via Ollama. To set up the Continue extensi…
Cursor is currently the more stable and feature-complete AI code editor with superior codebase indexing, while Windsurf offers a more cohesive agentic experience through its 'Flow' feature, according …
A developer compared Claude Fable 5 and GPT-4o on TypeScript code generation tasks, finding that each model has distinct failure modes. Claude Fable 5 is stronger with generics and strict mode but str…
A developer proposes a multi-model context management workflow that uses a local .context folder with markdown files (project-map.md, api-contracts.md, style-guide.md) as a version-controlled source o…
Tokenless, an API gateway for LLMs, reduces AI costs by dynamically routing requests between models based on complexity, matching Claude performance while cutting costs by 50%. The system queries mult…
A framework called the Agentic Method treats LLM output as a scientific record by enforcing a strict Domain Specific Language (DSL) with tags like (CTX), (H), and (VERDICT), evidence grading (F0-F4), …
Cursor's AI debugging tool automates fixes by indexing a local codebase with retrieval-augmented generation, but its accuracy depends on prompt specificity: clicking the "Fix" button yields only 30% f…