/
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

@beyang

@beyang
9 posts
2025-01-29
Congrats to the Block team for announcing this. We discovered goose awhile back when the code was first published, and already have more than one customer using this in conjunction with some as-yet unannounced features in production... more on this soon!
2025-01-29 View on X
ZDNET

Block introduces an on-device, open-source AI agent called Goose, which allows developers to choose their preferred LLM to automate engineering tasks

Radhika Rajkumar / ZDNET :

2024-07-27
In my experience as a founder, @DavidSacks has been nothing but helpful and supportive through a tumultuous period for startups. I hear the same from founder friends (many YC co's) that he has invested in. Outside of tech, one thing I appreciated was he joined @garrytan in
2024-07-27 View on X
TechCrunch

A decade-old drama between David Sacks and Parker Conrad blew up into a fight on X over VC behavior, drawing in Paul Graham and other big Silicon Valley names

Julie Bort / TechCrunch :

2024-07-26
In my experience as a founder, @DavidSacks has been nothing but helpful and supportive through a tumultuous period for startups. I hear the same from founder friends (many YC co's) that he has invested in. Outside of tech, one thing I appreciated was he joined @garrytan in
2024-07-26 View on X
TechCrunch

A decade-old drama between David Sacks and Parker Conrad has blown up into a fight on X over VC behavior, drawing in Paul Graham and other Silicon Valley names

A decade-old drama involving VC David Sacks and Rippling founder Parker Conrad over their previous company Zenefits has blown …

2024-05-30
Very nice survey of LLM best practices from practitioners building for real-world use cases. They even have a nice quote from yours truly on retrieval methods: https://www.oreilly.com/... [image]
2024-05-30 View on X
O'Reilly Media

Six AI and ML experts detail what they learned from building real-world applications on top of LLMs over the past year, including common prompting pitfalls

‘What We Learned from a Year of Building with LLMs (Part I)’  —  https://www.oreilly.com/...  Hallucinations are still a big problem; RAGs are better than fine-tuning; long context...

2024-05-07
Here's how we'll know: take the sergey brin boobsuit man and place him at a point equidistant from both houses. Whichever one he walks toward is the True AGI House. But if he sees his own shadow before taking a step, there will be 10 more years of AI winter.
2024-05-07 View on X
Forbes

A look at the trademark dispute over the name AGI House between two rival hacker houses, one in Hillsborough and the other in Twin Peaks in the Bay Area

to centralize power & capital. SF wants AGI Houses to blossom across the world to usher in the global intelligence age. Noah Smith / @noahpinion : This explains why whenever anyone...

2023-05-13
This is why LLM portability matters https://www.anthropic.com/.... If you're using Copilot, you have a 2-year old model with 2k tokens of context that doesn't know anything past 2021. If you're using Cody, you can use Claude, GPT-4, and the latest, greatest LLMs as they come online,... https://twitter.com/...
2023-05-13 View on X
TechCrunch

Anthropic expands Claude's context window from 9K to 100K tokens, or ~75K words it can digest and analyze; OpenAI's GPT-4 has a context window of ~32K tokens

2023-05-12
This is why LLM portability matters https://www.anthropic.com/.... If you're using Copilot, you have a 2-year old model with 2k tokens of context that doesn't know anything past 2021. If you're using Cody, you can use Claude, GPT-4, and the latest, greatest LLMs as they come online,... https://twitter.com/...
2023-05-12 View on X
TechCrunch

Anthropic expands Claude's context window from 9K to 100K tokens, or ~75K words it can digest and analyze; OpenAI's GPT-4 has a context window of ~32K tokens

Historically and even today, poor memory has been an impediment to the usefulness of text-generating AI.

2023-04-02
Twitter's algo is LIVE on @sourcegraph with FULL compiler-accurate code nav! 👇 https://sourcegraph.com/... https://twitter.com/...
2023-04-02 View on X
TechCrunch

Twitter open sources a portion of its code on GitHub, including its algorithm for recommending tweets in For You but excluding its ad recommendation algorithm

As repeatedly promised by Twitter CEO Elon Musk, Twitter has opened a portion of its source code, including the algorithm it uses …

2023-04-01
Twitter's algo is LIVE on @sourcegraph with FULL compiler-accurate code nav! 👇 https://sourcegraph.com/... https://twitter.com/...
2023-04-01 View on X
TechCrunch

Twitter open sources a portion of its code on GitHub, including its algorithm for recommending tweets in For You but excluding its ad recommendation algorithm

As repeatedly promised by Twitter CEO Elon Musk, Twitter has opened a portion of its source code, including the algorithm it uses …