benchmarking ai agents for java framework migration
scarfbench evaluates ai agents on real-world enterprise java framework migrations, measuring build, deploy, and behavioral success.
topic
tools
claude sonnet 5 arrives with new tokenizer and higher effective cost
anthropic's claude sonnet 5 launches with performance near opus 4.8, a new tokenizer that increases token counts by about 30% for english, and removal of temperature sampling parameters.
shot-scraper video records agent demos from yaml
shot-scraper 1.10 adds a video command that records browser demos defined in a storyboard yaml file, helping coding agents produce visual walkthroughs of their work.
every eval ever results now on hugging face model pages
every eval ever and hugging face community evals are now intercompatible, enabling cross-posting and interpreting evaluation results with links to open models and leaderboards.
miles: pytorch-native stack for large-scale llm rl post-training
miles is an open source framework that combines sglang, megatron-lm, ray, and pytorch for scalable reinforcement learning post-training of large language models.
7 python projects for 2026 with guides
practical python projects covering ai automation, machine learning, apis, dashboards, and data analysis with full guides and resources.
google releases nano banana 2 lite and gemini omni flash
google deepmind launches nano banana 2 lite for fast image generation and gemini omni flash for video generation and conversational editing.
local ai agents with qwen3.6 and mcp
build a local github assistant using qwen3.6-35b-a3b and the model context protocol to read issues, fix bugs, and create pull requests without cloud dependency.
why specialization is inevitable in ai
optimization theory, biology, markets, and machine learning all point to the same conclusion: under finite resources, focused systems outperform general ones.
ornith-1.0: self-scaffolding llms for agentic coding
deepreinforce releases ornith-1.0, an open weights model family for agentic coding built on gemma 4 and qwen 3.5, achieving top open-source coding benchmarks.
one transformer for density and score across distributions
discoformer estimates density and score in one forward pass without retraining, outperforming kernel density estimation in high dimensions.
best value ai coding subscription plans for developers
a comparison of five ai coding subscription plans that offer strong value through token, credit, or quota-based pricing.
pytorch adds cross-repo ci relay for backend testing
pytorch introduces a cross-repository ci relay that automatically triggers and tracks downstream ci, showing results on a single dashboard.
darts unifies zero-shot time series foundation models
darts introduces a unified interface for foundation models like chronos-2 and timesfm 2.5, simplifying zero-shot forecasting in python.
frontier model economics and export controls
dean w. ball argues that delays in ai model availability hurt labs' ability to recoup training costs and threaten the business case for massive infrastructure investments.
2,000 people tried to hack an ai assistant and failed
a public challenge to leak secrets from an ai assistant via email saw 6,000 attempts but no successful breaches, highlighting improved model defenses against prompt injection.
openai previews gpt-5.6 series with three model tiers
openai launches limited preview of gpt-5.6 models sol, terra, and luna, offering varied performance and pricing tiers with new prompt caching features.
fine-tune language models on apple silicon with mlx
fine-tune open language models locally on your mac using mlx, with no cloud gpus or costs required.