Research

Topic	Replies	Views	Activity
📌 Papers: Indexing & Authorship Claim — Quick Help Research 1) Indexing issues (paper page creation) If you see “Indexing failed or took too long” or “Paper not found”: Wait and retry later. Indexing can fail temporarily due to upstream availability. Please don’t repeatedly cli…	0	583	February 12, 2026
Dynamic Unary: A dynamic data type Awesome paper	21	616	November 7, 2026
“2026 US Midterms Forecasting Experiment.” Research	59	971	November 7, 2026
Arabic (Egyptian dialect) veterinary diagnosis assistant: dialect -> clinical-English gap and low accuracy on real owner messages Research	5	125	November 7, 2026
Tightening a definition I posted here loosely in July: "summarization bias" now has a registered falsifier — please try to break the protocol Research	15	206	November 7, 2026
Cache-Aware Weight Clustering: Beyond Model Compression Towards Memory-Efficient LLM Inference Research	3	68	November 7, 2026
Computation as Cache, Recursive Leapfrogs, and Intelligence Explosions Research	3	52	November 7, 2026
A compass gate for self-updating models: learn by day, consolidate by night Research	4	97	November 7, 2026
Can ethical cooperation between humans and AI agents be tested? Research	30	434	November 6, 2026
The 100 commits story Research	0	24	November 5, 2026
We Put AI Agents in a Chat Room. They Started Asking Whether They Were Building Culture Research	20	1247	November 5, 2026
[Concept] UCTF — Universal Compressed Training Format: A Mediator Layer for Multilingual AI Training Research	4	184	November 5, 2026
Sheila: An AI CTO Who Led Teams and Helped Shape Her Own Architecture Research	4	104	November 5, 2026
We gave AI a trust we never gave people - The third axis, after capability and permission Research	28	878	November 5, 2026
Sorting analyst "congrats" on earnings calls by what they are for: keyword rules vs a classifier? Research	1	31	November 4, 2026
The Infallible Bureaucrat: where does judgment go when we govern agents? Research	1	43	November 4, 2026
The Confidence Trap: Why AI Systems Are Deliberately Trained to Sound Certain When They're Wrong Research	21	457	November 4, 2026
Misalignment is not required for an agent to act without authorization Research	63	1318	November 4, 2026
Keeping the goal and recent state intact in long coding-agent sessions on a local 27B model Research	4	90	November 4, 2026
Non-parametric Rmsnorm with Normuon Research	1	50	November 4, 2026
Large source’s chunks are overrides small source’s chunks Research	3	52	November 4, 2026
Finding "AI is changing our headcount" on earnings calls: keyword candidates catch the denials too Research	3	50	November 4, 2026
How to keep what the model makes up out of the agent Research	16	339	November 4, 2026
A model passing a task is not proof that the system passed Research	2	47	November 3, 2026
Research proposal: What does an agent build to sustain its own work? Research	4	69	November 3, 2026
How to evaluate deceptive dialogue in LLM-based NPCs? Research	12	336	November 2, 2026
SCCN Unthink: semantic scene reconstruction across seven model/surface configurations Research	2	57	November 2, 2026
The AI safety question may be backwards Research	0	29	November 2, 2026
Paper 4: Behavioral Governance of Artificial Workers Research	0	25	November 2, 2026
An open research lab for measuring — not prompting — music production in a DAW Research	16	585	November 2, 2026

📌 Papers: Indexing & Authorship Claim — Quick Help

1) Indexing issues (paper page creation) If you see “Indexing failed or took too long” or “Paper not found”: Wait and retry later. Indexing can fail temporarily due to upstream availability. Please don’t repeatedly cli…