sepia
/
sepiatones_xyz
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: sepia:73d2e50be7e5b64962dd3f3eba3f53154eb443c3
Branches Tags
sepia:master
...
compare: sepia:232855e95213d86d955aefd009f71f32846e01e1
Branches Tags
sepia:master

3 Commits
73d2e50be7 ... 232855e952

Author SHA1 Message Date
sepia 232855e952 Add code link, and fix broken br tag in a post 2025-07-30 19:42:53 -05:00
sepia be87c90b47 Remove test post and move AI memory post 2025-07-30 14:06:03 -05:00
sepia 9bf45afc4b Post about AI memory 2025-07-30 14:05:19 -05:00
4 changed files with 38 additions and 14 deletions
Show Stats Expand all files Collapse all files

4
data/pages/about.html
View File

@ -37,7 +37,7 @@
</ul> </ul>
<br /> <br />
<p> <p>
This website was made with htmx and rust. I will not post the code unless This website was made with Elysia and HTMX. You can
you bother me about it, because I am lazy. <a href="https://git.sepiatones.xyz/sepia/sepiatones_xyz">read the code</a>.
</p> </p>
</article> </article>

8
data/posts/other_post.html
View File

@ -1,8 +0,0 @@
<head>
<meta name="title" content="Other Post" />
<meta name="date" content="2024-09-24T00:00:00Z" />
</head>
<article>
<h1>Welcome to another post!</h1>
<p>another one!</p>
</article>

4
data/posts/test_post.html
View File

@ -1,4 +0,0 @@
<article>
<h1>Test</h1>
<p>This is just a test!</p>
</article>

36
data/posts/things_ai_agents_should_be_able_to_do.html Normal file
View File

@ -0,0 +1,36 @@
<head>
<meta name="title" content="Things AI Agents Should Be Able to Do" />
<meta name="date" content="2025-07-30T00:00:00Z" />
</head>
<article>
<h1>Things AI Agents Should be Able to Do</h1>
<h2>Write Their Own Helper Scripts</h2>
<p>
If I ask my agent to play chess with me (or a game that doesn't exist), it
should write a basic chess engine, unmprompted, in a sandboxed environment,
which it can then use as a tool the next time it plays chess. Nobody has
implemented this yet because it requires a lot of agency from the agent, and
would have a bad error rate. I think it can be done effectively by limiting
the agent to a single tech stack and a railroaded workflow for creating its
own tools. Like a human software engineer, an AI agent should seek to
automate tedious tasks.
</p>
<h2>Forget</h2>
<p>
Humans still have better memories than LLMs, because we forget. Agents can
be fitted with a RAG to quickly memorize trivia, but if you have your agent
remembering everything it does all day, the database gets cluttered with
information that doesn't matter, and recall brings up a lot of garbage. This
effect would be exacerbated if you fed an agent a firehose of information
from your camera-glasses, which is exactly how much information your own
monkey brain is intaking.
<br />
Human memory should be used as a model: when information is repeated, we
remember it more strongly, and if it's not, we forget. Additionally, humans
spend time "alone with our thoughts" reflecting on our memories and creating
new super-memories that are much denser with useful information (For
example, you might remember "My friend James likes strawberry ice cream," a
reflection that allows you to throw away 200 instances of memories of him
ordering strawberry ice cream).
</p>
</article>