AllFeed, trending, and board
FeedLatest news
TrendingOpen source and releases
BoardBlogs and showcases
TagsBrowse by topic

#code-generation

The latest AI and developer news about #code-generation, with the original source and a short summary.

AI Briefing

Privacy Policy Terms of Service Contact About Sources RSS Support us

Feed
Trending
Tags
Settings

Ouroboros: A Debugger-Tracer for LLMs and Programmers That Records Actual Program Execution (All Calls, Arguments, Results) in 8 Languages

·2026.09.11 04:00

Continuous Diffusion Code Generation in a Few or Single Steps

·2026.09.08 07:00

When Code Becomes Abundant

·2026.08.25 09:00

Self-Review Errors in AI Agents and Solutions

·2026.08.17 21:00

PickMeta Launches Muse Code

·2026.08.09 08:00

Introducing Flex: Letting Models Write Code (16 min read)

·2026.08.06 09:00

GLM 5.2 Ranks 3rd on ProgramBench

·2026.07.23 02:00

Cursor Analyzes Cost of Multi-Agent Swarms

·2026.07.22 10:00

Qwen2.5-Coder Quantization Performance Study Results

·2026.07.20 16:00

The Shifting Cost of Approving Feature Requests

·2026.07.18 01:00

Report: Google's Gemini 3.5 Pro launch delayed

·1·2026.07.17 09:00

Simple Self-Distillation Improves LLM Code Generation Performance

·2026.07.16 09:00

New Code Benchmark DeepSWE Released

·1·2026.06.24 11:00

Cohere Unveils Code-Specialized Model North Mini Code

·2026.06.14 02:00

MooreThreads Unveils MusaCoder-27B Model

·2026.06.10 20:00

The Next Frontier of Visual AI Is Code

·2026.06.03 09:00

Constraint Decay: The Fragility of LLM Agents in Backend Code Generation

·2026.05.25 23:00

Constraint Decay: Vulnerability of LLM Agents in Backend Code Generation

·2026.05.24 21:00

Zero - A Programming Language for Agents

·1·2026.05.23 09:00

Qwen3.7-Max: agent frontier

·2026.05.21 09:00

Antigravity 2.0 Tops OpenSCAD Architectural 3D LLM Benchmark

·2026.05.21 09:00

Formal Verification Gates for AI Coding Loops

·2026.05.21 00:00

GPT-5.5 low vs medium vs high vs xhigh: The Reasoning Curve Seen Across 26 Real Tasks in an Open-Source Repository

·2026.05.09 11:00

ProgramBench: Can Language Models Rebuild Programs from Scratch

·2026.05.07 12:00

1
2
3
Next

1
2
3
Next

#code-generation | AI Briefing