Skip to main content
Scour
Discover
Docs
Offline · reconnecting…
System
Light
Dark
Login
Sign up
emschwartz's likes
+
Follow
840
interests
·
3,888
feeds
·
2,030
likes
Loves
Likes
🎲
Matched interest: Recommendation Systems. See more posts related to it
The evolution of modern recommender systems
Vinitha V N
7w
7 weeks ago
Substack
10 min read
Vinitha V N
Vinitha V N
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block vinithavn.substack.com
Actions for The evolution of modern recommender systems
🧠
Matched interest: Agent Memory. See more posts related to it
🥇Top AI Papers of the Week - AI Newsletter
AI Newsletter
7w
7 weeks ago
7 min read
AI Newsletter
elvis
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block nlp.elvissaravia.com
Actions for 🥇Top AI Papers of the Week - AI Newsletter
🏆
Matched interest: LLM Benchmarking. See more posts related to it
TERMINAL-BENCH
tbench.ai
7w
7 weeks ago
tbench.ai
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block tbench.ai
Actions for TERMINAL-BENCH
🔓
Matched interest: Open-Weight Models. See more posts related to it
An open letter to Dario: if you mean it, open the weights
jacob.gold
7w
7 weeks ago
HN
2 min read
jacob.gold
Covers 2 stories
We Must Pace the Frontier
,
Company
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block jacob.gold
Actions for An open letter to Dario: if you mean it, open the weights
🏆
Matched interest: LLM Benchmarking. See more posts related to it
Real-SWE Benchmark (new)
withspecific.com
7w
7 weeks ago
HN
Covered by
2
10 min read
withspecific.com
Janak Sunil
Covered by
2 sites
AI Benchmarks
,
and more ›
Covers 1 story
Frontier Code (AI coding benchmark)
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block withspecific.com
Actions for Real-SWE Benchmark (new)
⚡
Matched interest: Speculative Decoding. See more posts related to it
You Could Have Come Up with Speculative Decoding
amandeepsp.github.io
8w
8 weeks ago
HN
15 min read
amandeepsp.github.io
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block amandeepsp.github.io
Actions for You Could Have Come Up with Speculative Decoding
💻
Matched interest: Coding Agents. See more posts related to it
RTK reports token savings, but our cost benchmarks disagree
Quesma
7w
7 weeks ago
HN
5 min read
Quesma
Bartosz Kotrys
Jacek Migdal
Covers 3 stories
TERMINAL-BENCH
,
Does “rtk” skill really cut agent tokens by 60–90%? We tested it
,
and more ›
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block quesma.com
Actions for RTK reports token savings, but our cost benchmarks disagree
📝
Matched interest: WebFonts. See more posts related to it
Glide: variable UI font by Matthew Blode
blode.co
8w
8 weeks ago
2 min read
blode.co
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block blode.co
Actions for Glide: variable UI font by Matthew Blode
🤖
Matched interest: AI Engineering. See more posts related to it
Don't build tools for AI agents
Sean Goedecke
7w
7 weeks ago
HN
2
3 min read
Sean Goedecke
HN
2
newer thread
·
older thread
Covers 1 story
How do programming languages impact token efficiency and correctness?
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block seangoedecke.com
Actions for Don't build tools for AI agents
🔓
Matched interest: Open Source AI. See more posts related to it
Quoting huggingface.co/security.txt
Simon Willison’s Weblog
7w
7 weeks ago
Simon Willison’s Weblog
Simon Willison
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block simonwillison.net
Actions for Quoting huggingface.co/security.txt
🪄
Matched interest: Prompt Engineering. See more posts related to it
"Please Remove All Mannered Prose" and Other LLM Incantations
Matthew Ritch
7w
7 weeks ago
HN
10 min read
Matthew Ritch
Covers 1 story
Interpreting GPT: the logit lens – LessWrong(2020)
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block matthewritch.com
Actions for "Please Remove All Mannered Prose" and Other LLM Incantations
🏆
Matched interest: LLM Benchmarking. See more posts related to it
The Era of Agentic Benchmaxxing
The Kaitchup
8w
8 weeks ago
Substack
6 min read
The Kaitchup
Benjamin Marie
Covers 2 stories
Infrastructure configuration can swing coding evals by several % points
,
Muse Spark 1.3 Multimodal Evaluation Methodology
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block kaitchup.substack.com
Actions for The Era of Agentic Benchmaxxing
💾
Matched interest: Prompt Caching. See more posts related to it
DeepSeek V4 Flash Provider Cache Benchmark
olafdsouza.com
7w
7 weeks ago
HN
5 min read
olafdsouza.com
Olaf
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block olafdsouza.com
Actions for DeepSeek V4 Flash Provider Cache Benchmark
🎭
Matched interest: Social Engineering. See more posts related to it
A rant about phishing: It's not the user's fault (and not DNS either)
Maurycy's blog
7w
7 weeks ago
HN
2
2 min read
Maurycy's blog
HN
2
newer thread
·
older thread
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block maurycyz.com
Actions for A rant about phishing: It's not the user's fault (and not DNS either)
✨
Matched interest: GPT-6 Astra. See more posts related to it
GPT-6 Astra and the Fourth Exponential (6 minute read)
Key Context by Tae Kim
8w
8 weeks ago
Substack
4 min read
Key Context by Tae Kim
Tae Kim
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block taekim.substack.com
Actions for GPT-6 Astra and the Fourth Exponential (6 minute read)
🤝
Matched interest: Human-AI Interaction. See more posts related to it
Code Reviews in the Age of AI
danielfm.me
7w
7 weeks ago
HN
4 min read
danielfm.me
Daniel Martins
Covers 2 stories
Don't Be a Meat Proxy
,
I'm Becoming AI-Blind
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block danielfm.me
Actions for Code Reviews in the Age of AI
🛡️
Matched interest: AI Safety. See more posts related to it
Is it correct?
alexgaynor.net
8w
8 weeks ago
2 min read
alexgaynor.net
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block alexgaynor.net
Actions for Is it correct?
🤖
Matched interest: AI. See more posts related to it
The Pulse: tech companies move to open AI models
The Pragmatic Engineer
7w
7 weeks ago
HN
5 min read
The Pragmatic Engineer
Ivan Klaric
Covers 4 stories
Uber burned through its entire 2026 AI budget in four months. Now its COO is questioning whether it’s worth it
,
Cracks in the AI Thesis Part 2
,
and more ›
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block blog.pragmaticengineer.com
Actions for The Pulse: tech companies move to open AI models
⚔️
Matched interest: Trade War Economics. See more posts related to it
Retaliatory Canadian tariffs take effect
The Hill
7w
7 weeks ago
1 min read
The Hill
Sarah Davis
Covers 1 story
List of products from the United States subject to counter-tariffs effective September 8, 2026
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block thehill.com
Actions for Retaliatory Canadian tariffs take effect
🔎
Matched interest: AI Auditing. See more posts related to it
Measuring AI capabilities in intelligence targeting and conventional weapons
Anthropic
7w
7 weeks ago
HN
20 min read
Anthropic
Covers 1 story
Ukraine’s Future Vision and Current Capabilities for Waging AI-Enabled Autonomous Warfare
Read on Scour →
Love
Like
Dislike
Save
See related topics
Feeds
Share
Report
Spam
Misleading
Harmful Content
Block anthropic.com
Actions for Measuring AI capabilities in intelligence targeting and conventional weapons
« Page 8
·
Page 10 »
Sign in to enable infinite scrolling
Keyboard shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
Preview post
v
Post actions
Love post
a
Like post
l
Dislike
d
Undo reaction
u
Save / unsave
s
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Enable single-key shortcuts
Press
?
anytime to show this help
Keyboard shortcuts
·
Accessibility