Itch.io adding Generative AI disclosure filtering to few more places on the site
Itch.io is expanding its filters for games and other content disclosed as using generative AI. The filters will appear in more places across the site. (bsky.app)
Claude Opus 5.5 Can Draw Permit-Level Architectural Drawings
stephenjgallagher.substack.com99 points33 comments
An architect tested 13 AI models on technical drafting, arguing that a major capability shift arrived in 2026. In the first test, each model received rough sketches of a simple house and an example construction-document set, then had to create a complete set of drawings. Older models produced unusable or cartoonish results, and models released before September struggled with basic floor-plan layouts. Claude Opus 5.5 was the only model to correctly interpret the house’s dual-pitch roof and, after written feedback and two rounds of redlines, produced drawings the architect judged potentially good enough for a permit. The set still contained flaws, and the test involved more guidance for the strongest model than for weaker ones.
A second test asked Opus 5.5 to reconstruct a historic building’s plans, elevations, and details from photographs and rough field sketches, while matching the style of early-20th-century architect Frank Snyder. Its two finished sheets fell short of Snyder’s exceptional precision and retained subtle construction errors, but compared favorably with work from some architecture firms and took far less time and money than skilled human drafting. The drawings were editable vector linework, generated through Python code rather than CAD software or image-generation tools. Opus 5.5 spent about 12 hours and several hundred dollars on the house set, iteratively inspecting and revising its output. The author sees architects’ work shifting from direct drafting toward guiding and checking increasingly capable AI, while emphasizing that human expertise remains essential.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
More in AI
Sam Altman's Case Against Your RAM Is Efficient. That's the Problem
Sam Altman argues that people should use less RAM so memory can be redirected to AI data centers. Critics say OpenAI’s efforts to secure a large share of global RAM supplies could also drive up prices and question whether efficiency justifies restricting personal use. (techdirt.com)
AI agents hallucinate prices: LLM grounding with live data
LLMs often give outdated or incorrect product prices, even when they use web search. The tutorial shows how to build a Python agent that grounds answers in live data and lets code insert verified prices. (blog.apify.com)
Revolut moves to self-hosted GLM
Revolut moved about 2,000 engineers to self-hosted GLM coding models, running them on 56 Nvidia B200 GPUs at roughly $0.30 per million tokens. AI operations lead David Abitbol says engineering lead time improved 70% as lower costs let teams use AI more broadly, while Claude Code and Codex became exceptions. (twitter.com)
Could a modern chess engine on a Pentium have defeated Kasparov in 1996?
A 1995 Pentium Pro running a modern Stockfish port is estimated to play at 3300 Elo, far above Kasparov’s peak rating. The experiment shows how advances in chess algorithms could have beaten Kasparov without Deep Blue’s custom supercomputer hardware. (nicholas.carlini.com)
Open models can do 90 percent of agentic work at a twentieth of the cost
Gartner says open-weight models can handle about 90% of routine enterprise agent tasks at a fraction of the cost of closed models, while frontier models remain useful for complex reasoning. It expects companies to rely more on specialized open models, making the software harnesses that route tasks between models a key source of value. (theregister.com)