Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.lang.prolog > #14569
| From | Mild Shock <janburse@fastmail.fm> |
|---|---|
| Newsgroups | comp.lang.prolog |
| Subject | IntelliJ just created Mellum, its open source (Was: Prolog missed the Web 2.0 Bandwagon) |
| Date | 2025-06-20 21:18 +0200 |
| Message-ID | <1034c6f$136cd$1@solani.org> (permalink) |
| References | <1034bs9$1364p$1@solani.org> |
Prolog missed the Web 2.0 Bandwagon. Unlike web 1.0 which is static content. Web 2.0 is all about dynamic content, including building content incrementally. IntelliJ just created Mellum, its open source, their ghost texts are code snippets. So its more like recalling typing marcros, giving them a good guess. Not completing partial identifiers: Why Did JetBrains Create Mellum? https://www.youtube.com/watch?v=7TqkvVXKxFA LLM optimized for code-related tasks. https://huggingface.co/JetBrains/Mellum-4b-base Mild Shock schrieb: > Web 2.0 is all about incremental content! > > > don’t think it could really do > > the “ghost text” effect. > > It wouldn’t do the ghost text, only assist > it. There was a misunderstanding how “ghost > texts” work. Maybe you were thinking, that > the “ghost text” is part of the first response. > > But usually the “ghost text” is a second response: > > > waiting for completion candidates to be suggested > > Well you don’t use it for your primary > typing completion which is preferably fast. > The first response might give context information, > for the second request which provides a > different type of completion. > > But the first response is not responsible > for any timing towards the second request. > That anyway happens in the client. And it > doesn’t hurt if the first response is > from a stupid channel. > > Web 2.0 is all about incremental content!
Back to comp.lang.prolog | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
Prolog missed the Web 2.0 Bandwagon Mild Shock <janburse@fastmail.fm> - 2025-06-20 21:13 +0200
IntelliJ just created Mellum, its open source (Was: Prolog missed the Web 2.0 Bandwagon) Mild Shock <janburse@fastmail.fm> - 2025-06-20 21:18 +0200
Re: IntelliJ just created Mellum, its open source (Was: Prolog missed the Web 2.0 Bandwagon) Mild Shock <janburse@fastmail.fm> - 2025-06-20 21:41 +0200
timers and tasks testing framework Node.js v20.0.0] (Was: IntelliJ just created Mellum, its open source) Mild Shock <janburse@fastmail.fm> - 2025-06-23 13:05 +0200
The magical "async" keyword again [Node.js v20.0.0] (Was: timers and tasks testing framework [Node.js v20.0.0]) Mild Shock <janburse@fastmail.fm> - 2025-06-23 13:10 +0200
OpenAPI Specification (OAS) goes full Monty [AsyncAPI] (Was: The magical "async" keyword again [Node.js v20.0.0]) Mild Shock <janburse@fastmail.fm> - 2025-06-24 08:16 +0200
OpenAPI Specification (OAS) goes full Monty [AsyncAPI] (Was: The magical "async" keyword again [Node.js v20.0.0]) Mild Shock <janburse@fastmail.fm> - 2025-06-24 08:17 +0200
constant caching test case / Prolog orthodoxification (Was: Prolog missed the Web 2.0 Bandwagon) Mild Shock <janburse@fastmail.fm> - 2025-06-24 01:06 +0200
Teachers have better quality than Nerds (Was: constant caching test case / Prolog orthodoxification) Mild Shock <janburse@fastmail.fm> - 2025-06-24 01:12 +0200
ISO is loosing it because it gives in to Teachers (Was: Teachers have better quality than Nerds) Mild Shock <janburse@fastmail.fm> - 2025-06-24 01:26 +0200
Where APIs Meet AI: Building Tomorrow's Intelligent Ecosystems (Was: ISO is loosing it because it gives in to Teachers) Mild Shock <janburse@fastmail.fm> - 2025-06-24 08:24 +0200
A library(pio) for the Web 2.0 (Was: Prolog missed the Web 2.0 Bandwagon) Mild Shock <janburse@fastmail.fm> - 2025-06-25 15:17 +0200
Corr. (Was: A library(pio) for the Web 2.0) Mild Shock <janburse@fastmail.fm> - 2025-06-25 15:19 +0200
csiph-web