Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
How to Run LLMs Locally on a Mac in 2027 (Even with 8GB or 16GB)
mehmet akar
mehmet akar
mehmet akar
Follow
Nov 21
How to Run LLMs Locally on a Mac in 2027 (Even with 8GB or 16GB)
#
llm
#
macos
#
ai
#
tutorial
Comments
Add Comment
16 min read
Moderation
I let coding agents use my Android phone, then made one run on the phone's NPU
ghorbelhamdi
ghorbelhamdi
ghorbelhamdi
Follow
Nov 21
I let coding agents use my Android phone, then made one run on the phone's NPU
#
android
#
ai
#
opensource
#
llm
Comments
1
comment
3 min read
Moderation
Keeping a 3B model honest: source-checked song facts for live streams
Christopher Feyrer
Christopher Feyrer
Christopher Feyrer
Follow
Nov 21
Keeping a 3B model honest: source-checked song facts for live streams
#
llm
#
opensource
#
electron
#
music
Comments
Add Comment
5 min read
Moderation
The most dangerous AI claims aren’t wrong — they’re overstated
MultiO
MultiO
MultiO
Follow
Nov 21
The most dangerous AI claims aren’t wrong — they’re overstated
#
productivity
#
ai
#
llm
#
machinelearning
Comments
Add Comment
2 min read
Moderation
37.1 MiB/s with Zero Token Overflows: Guaranteed Token Budgets and Table-Aware Chunking in text-chipper
Omer Cihangiroglu
Omer Cihangiroglu
Omer Cihangiroglu
Follow
Nov 21
37.1 MiB/s with Zero Token Overflows: Guaranteed Token Budgets and Table-Aware Chunking in text-chipper
#
rag
#
python
#
rust
#
llm
Comments
Add Comment
5 min read
Moderation
Why AI Apps Crash Under Real Traffic (And How to Fix It in 2 Lines)
rohan9024
rohan9024
rohan9024
Follow
Nov 21
Why AI Apps Crash Under Real Traffic (And How to Fix It in 2 Lines)
#
ai
#
node
#
openai
#
llm
Comments
Add Comment
6 min read
Moderation
Why your LLM is slow twice, and why it runs out of memory: prefill, decode and the KV cache
Deployed Lab
Deployed Lab
Deployed Lab
Follow
Nov 21
Why your LLM is slow twice, and why it runs out of memory: prefill, decode and the KV cache
#
ai
#
llm
#
gpu
#
machinelearning
Comments
Add Comment
3 min read
Moderation
YodaMan 0.6.7 and Context Expert 1.4.0: we wrote down what our tool does, and found 50 bugs
Trust Mutemasango
Trust Mutemasango
Trust Mutemasango
Follow
Nov 21
YodaMan 0.6.7 and Context Expert 1.4.0: we wrote down what our tool does, and found 50 bugs
#
developer
#
llm
#
softwaredevelopment
#
tools
Comments
Add Comment
5 min read
Moderation
The AI-Assisted Riemann Hypothesis Proof: What Independent Checks Actually Show
Mahan Tavakoli
Mahan Tavakoli
Mahan Tavakoli
Follow
Nov 21
The AI-Assisted Riemann Hypothesis Proof: What Independent Checks Actually Show
#
ai
#
claude
#
llm
#
science
Comments
Add Comment
5 min read
Moderation
Dify 1.20 Architecture Guide: OpenTelemetry Tracing, Human-in-the-Loop Messaging Gates, and Enterprise Migration
Ahmad
Ahmad
Ahmad
Follow
Nov 21
Dify 1.20 Architecture Guide: OpenTelemetry Tracing, Human-in-the-Loop Messaging Gates, and Enterprise Migration
#
dify
#
ai
#
humanintheloop
#
llm
Comments
Add Comment
7 min read
Moderation
The Eval Pyramid, Part I: Testing Systems That Don't Behave the Same Way Twice
Bharadwaj P
Bharadwaj P
Bharadwaj P
Follow
Nov 21
The Eval Pyramid, Part I: Testing Systems That Don't Behave the Same Way Twice
#
ai
#
llm
#
testing
#
agents
Comments
Add Comment
9 min read
Moderation
Your agent's success rate barely moved. One tool's error rate tripled.
GermanGerken
GermanGerken
GermanGerken
Follow
Nov 21
Your agent's success rate barely moved. One tool's error rate tripled.
#
ai
#
llm
#
observability
#
opensource
Comments
Add Comment
5 min read
Moderation
We hid codes in 7 social media posts and asked 5 AI assistants to find them
Programming with Jack Chew
Programming with Jack Chew
Programming with Jack Chew
Follow
Nov 21
We hid codes in 7 social media posts and asked 5 AI assistants to find them
#
ai
#
llm
#
opensource
#
benchmark
Comments
Add Comment
3 min read
Moderation
Why I removed the dedup from my coding agent
Sakshi Lunawat
Sakshi Lunawat
Sakshi Lunawat
Follow
Nov 21
Why I removed the dedup from my coding agent
#
llm
#
ai
#
firstpost
Comments
Add Comment
4 min read
Moderation
LightningMoBA: 71% Faster 50k‑Token Story Generation in Seconds!
amrit
amrit
amrit
Follow
Nov 21
LightningMoBA: 71% Faster 50k‑Token Story Generation in Seconds!
#
llm
#
attentionmechanism
#
neurips2026
#
ai
Comments
Add Comment
6 min read
Moderation
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account