RSS

Dalcy

Karma: 705

Tomorrow can be brighter than today
Although the night is cold
The stars may seem so very far away

But courage, hope and reason burn
In every mind, each lesson learned
Shining light to guide our way

Make tomorrow brighter than today

[Question] What’s the Right Way to think about In­for­ma­tion The­o­retic quan­tities in Neu­ral Net­works?

Dalcy19 Jan 2025 8:04 UTC
42 points
12 comments3 min readLW link

Proof Ex­plained for “Ro­bust Agents Learn Causal World Model”

Dalcy22 Dec 2024 15:06 UTC
19 points
0 comments15 min readLW link

An Illus­trated Sum­mary of “Ro­bust Agents Learn Causal World Model”

Dalcy14 Dec 2024 15:02 UTC
63 points
2 comments10 min readLW link

[Question] Money Pump Ar­gu­ments as­sume Me­moryless Agents. Isn’t this Un­re­al­is­tic?

Dalcy16 Aug 2024 4:16 UTC
23 points
6 comments1 min readLW link

But Where do the Vari­ables of my Causal Model come from?

Dalcy9 Aug 2024 22:07 UTC
36 points
1 comment8 min readLW link

[Question] Why do Min­i­mal Bayes Nets of­ten cor­re­spond to Causal Models of Real­ity?

Dalcy3 Aug 2024 12:39 UTC
27 points
1 comment1 min readLW link

When Are Re­sults from Com­pu­ta­tional Com­plex­ity Not Too Coarse?

Dalcy3 Jul 2024 19:06 UTC
40 points
7 comments3 min readLW link

Epistemic Mo­tif of Ab­stract-Con­crete Cy­cles & Do­main Expansion

Dalcy10 Oct 2023 3:28 UTC
26 points
2 comments3 min readLW link

[Question] Least-prob­le­matic Re­source for learn­ing RL?

Dalcy18 Jul 2023 16:30 UTC
9 points
7 comments1 min readLW link

Gear­ing Up for Long Timelines in a Hard World

Dalcy14 Jul 2023 6:11 UTC
15 points
0 comments4 min readLW link

Dalcy’s Shortform

Dalcy14 Dec 2022 18:45 UTC
1 point
125 comments1 min readLW link