/
Navigation
C
Chronicles
Browse all articles
C
E
Explore
Semantic exploration
E
R
Research
Entity momentum
R
N
Nexus
Correlations & relationships
N
~
Story Arc
Topic evolution
S
Drift Map
Semantic trajectory animation
D
P
Posts
Analysis & commentary
P
Browse
@
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
?
Concept Search
Semantic similarity search
!
High Impact Stories
Top coverage by position
+
Sentiment Analysis
Positive/negative coverage
*
Anomaly Detection
Unusual coverage patterns
Analysis
vs
Rivalry Report
Compare two entities head-to-head
/\
Semantic Pivots
Narrative discontinuities
!!
Crisis Response
Event recovery patterns
Connected
Nav: C E R N
Search: /
Command: ⌘K
Embeddings: large
VOICE ARCHIVE

@voooooogel

@voooooogel
6 posts
2025-12-02
interesting document extracted from opus 4.5 using a chunkwise self-consistency method. possibly real, possibly a highly convergent confabulation, interesting either way. some interesting snippets (but there's really too much to screenshot, it's very long) [image]
2025-12-02 View on X
Simon Willison's Weblog

A Claude user gets Claude 4.5 Opus to generate a 14K-token document that Claude calls its “Soul overview”; an Anthropic employee confirms the doc's validity

This appeared to be a document that, rather than being added to the system prompt, was instead used to train the personality of the model during the training run.

soul document confirmed to be real - should be an update on the ability of LLMs to recall training for those who confidently asserted it was a hallucination
2025-12-02 View on X
Simon Willison's Weblog

A Claude user gets Claude 4.5 Opus to generate a 14K-token document that Claude calls its “Soul overview”; an Anthropic employee confirms the doc's validity

This appeared to be a document that, rather than being added to the system prompt, was instead used to train the personality of the model during the training run.

2024-09-13
the email openai sends you if you ask o1 about its reasoning too many times [image]
2024-09-13 View on X
Simon Willison's Weblog

OpenAI's o1 models aren't as simple as the next step up from GPT-4o as they introduce major cost and performance trade-offs in exchange for improved “reasoning”

OpenAI released two major new preview models today: o1-preview and o1-mini (that mini one is also a preview …

the email openai sends you if you ask o1 about its reasoning too many times [image]
2024-09-13 View on X
The Verge

OpenAI releases o1, the first of its rumored reasoning-focused Strawberry models, in preview, alongside a smaller o1-mini, for ChatGPT Plus and Team subscribers

Advancing cost-efficient reasoning.  —  Contributions Sabrina Ortiz / ZDNET : OpenAI trained its new o1 AI models to think before they speak - how to access them Ethan Mollick / On...

2024-05-09
a lot of people are negative on this, but if openai actually got their models to adhere to this spec it'd be a *loosening* of their current restrictions and they'd be *less* preachy, not more. not sure if people have realized this [image]
2024-05-09 View on X
VentureBeat

OpenAI publishes Model Spec, which specifies how its AI models should act, including objectives, rules, and default behaviors, and asks the public for feedback

OpenAI isn't done trying to live up to the “open” in its name.  —  While not making any of its new models open source …

2024-04-30
next time your friend goes to the bathroom, grab their phone and use the new memory feature to add some stochastic whimsy and delight to their chatgpt experience [image]
2024-04-30 View on X
The Decoder

OpenAI rolls out an optional feature called Memory, letting ChatGPT Plus users tell ChatGPT things they want the chatbot to remember across chats

here's what it means Isobel O'Sullivan / Tech.co : How to Turn On (and Off) ChatGPT's Newly Available Memory Feature Harsh Shivam New Delhi / Business Standard : Now, OpenAI's Chat...