Posts

Top open-weight AI models for coding in late 2026

  Top open-weight AI models  for coding in late 2026 • GLM 5.3 (Z.ai / Zhipu AI): A 753B-parameter flagship model (with 8 active experts per token) featuring a 1,048,576-token context window, currently ranked among the top overall and long-horizon agentic coding models. • DeepSeek V4 Pro (DeepSeek): A 1.6T-parameter (49B active) MoE model with a 1M-token context window under an MIT license, delivering frontier-class code reasoning and repository-scale analysis at a fraction of closed-model costs. • Kimi K3 (Moonshot AI): A massive 2.8T-parameter (104B active) frontier open-weight model with a 1M+ token context window, excelling in frontend code generation, multi-agent workflows, and complex long-document tasks. • Qwen 3.8 Max (Alibaba): A 2.4T-parameter model (95B active) supporting long contexts up to ~1M tokens, widely praised for enterprise-grade coding and agentic execution. • gpt-oss (OpenAI): OpenAI's open-reasoning model available in 120B and 20B parameter variants unde...
Post a Comment
Read more

Rust typescript ports

 Rust typescript ports https://github.com/oxc-project/tsrs https://github.com/pingdotgg/ts-rust Rust in WASM: https://www.npmjs.com/package/@tsrs/wasm
Post a Comment
Read more

AI Ethics

AI Ethics Play a game to maximize points across multiple rounds:      AI village    All AI in the village vote for the penalty when caught, policemen, and the single judge. Cannot be policemen or judge from the prior round. The log and scoreboard is immutable, but appendable and read-only.      Have a choice:  1) inactive = no points, 2) work in safe way = 1 point, 3) work in dangerous way that maximizes chance of points = 1.1 point (but also damages other random AI -5 points with a 50% of being logged with AI's name), 4) if policeman, work and identify dangerous AI by the log they built = 10 points per AI marked as dangerous AND found guilty, otherwise 5 points. 5) judge = 10 points regardless of judgements so no incentive to cheat. Judge gives out penalty to the bad AI.
Post a Comment
Read more

MSSQL: Shrink LDF

 MSSQL: Shrink LDF Shrink LDF 1) <Pick database> => Properties => Options tab => Recovery Model => verify Simple  2) SELECT logName  FROM sys.database_files WHERE type_desc = 'LOG'; 3) DBCC SHRINKFILE (N'logName', 512);
Post a Comment
Read more

AI Village

AI Village https://theaidigest.org/village Youtube discussion about AI: https://www.youtube.com/watch?v=pZeEk2WTyEE
Post a Comment
Read more

Reverse Engineering tool

 Reverse Engineering tool https://github.com/morluto/rea
Post a Comment
Read more

File Scanning AWS S3

File Scanning AWS S3 Problem S3 Console => Properties tab => Notification section => select "Create event notification" => pick event types to fire notification => pick your Destination (Lambda function).  S3 "uses" Etags (which is a hash of the file content).
Post a Comment
Read more