LongChang tests whether LLMs discover altered physical laws unaided
Of 12 models, only GPT-6-Astra found a law, at a 16.7% discovery rate; the other 11 scored 0%.
42
- Mentions · 7d3
- Mentions · 30d12
- All mentions16
- First seenSep 5, 2026
- Last mentioned3d ago
Timeline
16 articles · newest firstLongChang tests whether LLMs can discover altered physical laws
Among 12 models, only GPT-6-Astra discovered laws, at a reported rate of 16.7 percent.
42
GPT-6-Astra evaluated on EBench for direct and policy-harness robot control
Direct control leads on short tasks but lags on long-horizon work; calling a VLA or WAM matches top policies at lower token cost.
46
WildAWM synthesizes environments for computer-use agent training
The open-source pipeline made 341 long-horizon tasks; GPT-6-Astra solved 60%, and two trained Qwen models improved on eight benchmarks.
52
LeakBench audits clinical agents for prediction-time leakage
DeepSeek Flash and GPT-6-astra leaked in 10 of 10 unconstrained September runs and in none when an admission-time constraint was set.
50
WildAWM synthesizes computer-use agent environments with open models
It yields 341 tasks that can exceed 100 steps; GPT-6-Astra solves 60%, and Qwen models trained only there improve on eight benchmarks.
52
HexaShell coding-agent harness sets a new RoboDojo score
With Codex and GPT-6-Astra, success is 39.7% on 42 tasks; tight insertion is 8.3% while pushing reaches 92.5%.
48
Video Game Reverse Engineering Community Shuts Down Because AI Has Made It Too Easy
decomp.dev is shutting down after AI made game decompilation and cloning trivial, overwhelming human-led projects.
46
GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece
OpenAI's GPT-6-Astra solved 49 of 50 routine theoretical-physics problems at about $2.40 each.
58
Authors say GPT-6-Astra has competence, not practical intelligence
Authors report strong benchmark results with in-context learning, but real robots still face costly demos and time limits.
52
BlenderWorld benchmarks frontier models on real-world 3D creation
GPT-6-Astra scored 79.9 overall, ahead of Opus-5 at 73.0 and GPT-5.6-Sol at 67.7.
44
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
Researchers introduce HSS, where humans score 93.1% and GPT-6-astra only 53.6% on intuitive visual reasoning.
48
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
LEGO-Anything uses coding agents to rebuild editable 3D scenes as executable Blender programs.
50
OpenAI Launches the Agents API in Public Beta, Putting the Codex Harness Behind One API Call
OpenAI released its Agents API in public beta, exposing the managed Codex harness with hosted or self-hosted sandboxes, MCP tools, and subagents.
78
OpenAI Agents API
OpenAI's Agents API documentation describes a managed Codex harness offering sandboxed agents, MCP connectivity, subagents, and US-only data residency.
60
Using Blender with coding agents on macOS
Simon Willison demonstrates driving the Blender macOS app with ChatGPT Codex coding agents to render scenes via Python, costing roughly $4.24 at API rates.
25
Appears with
- OpenAIorganization · 4
- Codexproduct · 4
- OpenAIvendor · 4
- Qwenai model · 2
- Agents APIproduct · 2
- Blenderproduct · 2
- InternRoboticsorganization · 1
- RoboDojoproduct · 1
- LeakBenchproduct · 1
- Gemini 3.8 Flashai model · 1
- DeepSeekorganization · 1
- HexaShellproduct · 1
- ChatGPT Codexproduct · 1
- DeepSeek Flashai model · 1
- Hugging Faceorganization · 1
- Blendervendor · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.