Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
LLMs
🧠 LLMs
Specific
large language models, GPT, Claude, inference
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
951
posts in
9.6
ms
Google's new open-weights
model
brings image-generation tricks to AI text generation
🤖
AI Engineering
Content type:
News
theregister.com
·
1d
1 day ago
·
Hacker News
Actions for Google's new open-weights model brings image-generation tricks to AI text generation
LLM
are universal simulators
🛡️
AI Safety
invertedpassion.com
·
4d
4 days ago
·
Hacker News
Actions for LLM are universal simulators
Ask HN: Any Local
LLM
can I run without GPU for Local Agentic workflow AI?
🤝
AI Agents
Content type:
Discussion
news.ycombinator.com
·
1d
1 day ago
·
Hacker News
Actions for Ask HN: Any Local LLM can I run without GPU for Local Agentic workflow AI?
DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200
🤖
AI Engineering
Content type:
News
newsletter.semianalysis.com
·
3d
3 days ago
·
Hacker News
·
Cited by 1 article
Actions for DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200
Franklin Templeton, BNP Paribas see
tokenization
boosting EU's capital efficiency
🖥️
Backend Development
cointelegraph.com
·
1d
1 day ago
Actions for Franklin Templeton, BNP Paribas see tokenization boosting EU's capital efficiency
Acoda: Adversarial Code Obfuscation for Defending against
LLM-based
Analysis
🔍
RAG
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis
How
LLMs
Actually Work: A Friendly Map for Humans • oreoro
🔍
RAG
oreoro.github.io
·
6d
6 days ago
·
Hacker News
Actions for How LLMs Actually Work: A Friendly Map for Humans • oreoro
Making FlashAttention-4 faster for
inference
📐
System Design
Content type:
Blog
modal.com
·
1d
1 day ago
·
Hacker News
Actions for Making FlashAttention-4 faster for inference
TradFi advisors want stablecoins,
tokenization
over Bitcoin: Bitwise
📐
System Design
cointelegraph.com
·
1d
1 day ago
Actions for TradFi advisors want stablecoins, tokenization over Bitcoin: Bitwise
Running Qwen 35B MoE at 450k
Context
on a Single 32GB GPU
📐
System Design
local-llm.utop.workers.dev
·
5d
5 days ago
·
Hacker News
·
Cited by 1 article
Actions for Running Qwen 35B MoE at 450k Context on a Single 32GB GPU
LLM
Cheat Sheet
🔍
RAG
Content type:
Blog
drkpxl.bearblog.dev
·
1d
1 day ago
Actions for LLM Cheat Sheet
TOON: Beyond JSON for
LLMs
🤖
AI Engineering
Content type:
Blog
towardsai.net
·
4d
4 days ago
Actions for TOON: Beyond JSON for LLMs
NVIDIA RTX Pro 6000 Blackwell: 96GB GDDR7 and the End of VRAM Anxiety
🤖
AI Engineering
Content type:
Blog
fitservers.com
·
3d
3 days ago
Actions for NVIDIA RTX Pro 6000 Blackwell: 96GB GDDR7 and the End of VRAM Anxiety
Does ChatGPT need a psychiatrist? Similarities between human psychopathology and errors in
large
language
models
🔍
RAG
Content type:
Academic
nature.com
·
2d
2 days ago
·
Hacker News
Actions for Does ChatGPT need a psychiatrist? Similarities between human psychopathology and errors in large language models
My Notes on the Progression from
Context
to Prompt to Harness engineering in making
GPT
LLMs
Useful: (TUESDAY) MAMLMs
🤖
AI Engineering
Content type:
News
Content type:
Blog
braddelong.substack.com
·
3d
3 days ago
·
Substack
Actions for My Notes on the Progression from Context to Prompt to Harness engineering in making GPT LLMs Useful: (TUESDAY) MAMLMs
Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir
🤖
AI Engineering
Content type:
Code
github.com
·
9h
9 hours ago
·
Hacker News
·
Cited by 1 article
Actions for Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir
ChatGPT easily bypasses its own guardrails; all
LLMs
are inherently unsafe
🛡️
AI Safety
Content type:
Blog
techzine.eu
·
6d
6 days ago
Actions for ChatGPT easily bypasses its own guardrails; all LLMs are inherently unsafe
NVIDIA A100 vs RTX 4090 for AI Workloads: The Cost Per FLOP Reality
📐
System Design
Content type:
Blog
fitservers.com
·
3d
3 days ago
Actions for NVIDIA A100 vs RTX 4090 for AI Workloads: The Cost Per FLOP Reality
Token4Token —
pay-per-token
inference
on Gnosis + Swarm
🤖
AI Engineering
t4t.eth.link
·
3d
3 days ago
·
Hacker News
Actions for Token4Token — pay-per-token inference on Gnosis + Swarm
Latest technical articles & videos.
🤖
AI Engineering
certdepot.net
·
6d
6 days ago
Actions for Latest technical articles & videos.
Sign up or log in to see more results
Sign Up
Login
« Page 2
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help