| … | … | @@ -9189,6 +9189,94 @@ fuck it. |
| 9189 | 9189 | |
| 9190 | 9190 | And then my code scales out of control and I am back to theorizing again. |
| 9191 | 9191 | Except now five years have slipped by. |
| 9192 | \end_layout |
| 9193 | |
| 9194 | \begin_layout Standard |
| 9195 | The meta question is |
| 9196 | \begin_inset Quotes eld |
| 9197 | \end_inset |
| 9198 | |
| 9199 | what should I build? |
| 9200 | \begin_inset Quotes erd |
| 9201 | \end_inset |
| 9202 | |
| 9203 | and |
| 9204 | \begin_inset Quotes eld |
| 9205 | \end_inset |
| 9206 | |
| 9207 | How should I build it? |
| 9208 | \begin_inset Quotes erd |
| 9209 | \end_inset |
| 9210 | |
| 9211 | . |
| 9212 | The very first part involves this idea that |
| 9213 | \begin_inset Quotes eld |
| 9214 | \end_inset |
| 9215 | |
| 9216 | I want to perceive file systems |
| 9217 | \begin_inset Quotes erd |
| 9218 | \end_inset |
| 9219 | |
| 9220 | , |
| 9221 | but the proximal perception code, |
| 9222 | of pair–counting, |
| 9223 | does not yet exist. |
| 9224 | Worse, |
| 9225 | if it existed but was tuned for texts, |
| 9226 | it could not perceive file systems ... |
| 9227 | or perhaps more directly, |
| 9228 | it could not perceive the |
| 9229 | \begin_inset Quotes eld |
| 9230 | \end_inset |
| 9231 | |
| 9232 | AtomSpace itself |
| 9233 | \begin_inset Quotes erd |
| 9234 | \end_inset |
| 9235 | |
| 9236 | . |
| 9237 | \end_layout |
| 9238 | |
| 9239 | \begin_layout Standard |
| 9240 | I sort of tripped over this last idea, |
| 9241 | working on the AtomSpace visualizer. |
| 9242 | I have a large dataset. |
| 9243 | I have kind of forgotten |
| 9244 | \begin_inset Quotes eld |
| 9245 | \end_inset |
| 9246 | |
| 9247 | whats in there |
| 9248 | \begin_inset Quotes erd |
| 9249 | \end_inset |
| 9250 | |
| 9251 | , |
| 9252 | and I wanted to get a quick reminder of what it was. |
| 9253 | Well, |
| 9254 | there are two ways. |
| 9255 | One way is to build something into the visualizer, |
| 9256 | provide a whole bunch of buttons and visualizer do–hickies, |
| 9257 | and click on them, |
| 9258 | and get some general idea of what's in there. |
| 9259 | The other way is to start a CogServerNode, |
| 9260 | and ask Claude to connect to the CogServer, |
| 9261 | and verbally inquire |
| 9262 | \begin_inset Quotes eld |
| 9263 | \end_inset |
| 9264 | |
| 9265 | what's in here? |
| 9266 | and |
| 9267 | \begin_inset Quotes eld |
| 9268 | \end_inset |
| 9269 | |
| 9270 | how is it structured? |
| 9271 | and try to get OK answers via natural language query. |
| 9272 | Which is kind of simpler than building the visualizer, |
| 9273 | which is ... |
| 9274 | hard. |
| 9275 | Hmm. |
| 9276 | I have not tried to have the MCP–examination of this dataset. |
| 9277 | Maybe I should try that, |
| 9278 | and see what happens, |
| 9279 | see if I can get meaningul enlightenment that way ... |
| 9192 | 9280 | |
| 9193 | 9281 | \end_layout |
| 9194 | 9282 | |