- From: Sebastian Samaruga <ssamarug@gmail.com>
- Date: Fri, 12 Jun 2026 12:33:47 -0300
- To: Melvin Carvalho <melvincarvalho@gmail.com>
- Cc: W3C Semantic Web IG <semantic-web@w3.org>, W3C AIKR CG <public-aikr@w3.org>
- Message-ID: <CAOLUXBvta35OWYo4mXH5U0_bXAt61v90q=zJLmg2sWnJw-4FsQ@mail.gmail.com>
This is what AI thinks about AI: https://chatgpt.com/share/6a2c26c5-eab0-83e9-a20b-f4f5807e8e26 https://share.gemini.google/5kqbNH6fps7o On Fri, Jun 12, 2026, 12:17 PM Melvin Carvalho <melvincarvalho@gmail.com> wrote: > > > pá 12. 6. 2026 v 17:13 odesílatel Sebastian Samaruga <ssamarug@gmail.com> > napsal: > >> Question: >> >> Which sense does it make to still asking LLMs coding agents to generate >> code in languages created to be edited by humans in those languages. >> >> The source of the browser centered web was about pages source files >> easily editable by humans in text editors. We are still targeting our >> generated "applications" to those languages and what they have evolved to >> for our implementations. >> >> What about an intermediate "agent application language", auditable by >> humans, representation generated by the agents model and then compiled in, >> still browser centric, I think about WASM here. >> >> And what about if this agent "application language" could leverage >> natively AI models inference capabilities providing prompted / generated >> applications with those capabilities. >> >> Maybe I'm missing something, comments are welcome. Thanks! >> > > Web technologies are already a human-auditable agent language: HTML, CSS, > JS, JSON(-LD), Markdown. WASM can be a compilation target for performance, > but humans read and verify web-native formats best. Agents should generate > clear, declarative web apps, optionally leveraging WASM underneath. > > >> >> https://sebxama.blogspot.com/2026/06/ai-application-language.html >> >> Sebastián. >> >>
Received on Friday, 12 June 2026 15:34:23 UTC