Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Why Identity-Framing Jailbreaks Bypass Your LLM Safety Filters
Alan West
Alan West
Alan West
Follow
May 2
Why Identity-Framing Jailbreaks Bypass Your LLM Safety Filters
#
ai
#
security
#
llm
#
machinelearning
1
 reaction
Comments
Add Comment
5 min read
LLM Foundry finally stops being a toy and starts acting like a system
Aman Sachan
Aman Sachan
Aman Sachan
Follow
May 3
LLM Foundry finally stops being a toy and starts acting like a system
#
ai
#
llm
#
python
#
opensource
Comments
Add Comment
3 min read
The Math Behind Local LLMs: How to Calculate Exact VRAM Requirements Before You Crash Your GPU
Taz / ByteCalculators
Taz / ByteCalculators
Taz / ByteCalculators
Follow
May 2
The Math Behind Local LLMs: How to Calculate Exact VRAM Requirements Before You Crash Your GPU
#
ai
#
llm
#
machinelearning
#
tutorial
Comments
Add Comment
3 min read
The Limits of AI Models: What LLMs Still Can't Do (And Why)
Marko Frei
Marko Frei
Marko Frei
Follow
Jun 5
The Limits of AI Models: What LLMs Still Can't Do (And Why)
#
ai
#
llm
#
machinelearning
#
programming
5
 reactions
Comments
Add Comment
6 min read
"A Survey of LLM-based Deep Search Agents" (2026)
24P-0748 Arham Ali
24P-0748 Arham Ali
24P-0748 Arham Ali
Follow
May 7
"A Survey of LLM-based Deep Search Agents" (2026)
#
agents
#
ai
#
llm
#
rag
Comments
1
 comment
2 min read
LLM Observability Tools Compared: The 2026 Landscape
grepture
grepture
grepture
Follow
May 2
LLM Observability Tools Compared: The 2026 Landscape
#
ai
#
webdev
#
agents
#
llm
Comments
Add Comment
5 min read
I built an AI chat app because I was tired of AI sounding like a corporate memo
MemeChatAI
MemeChatAI
MemeChatAI
Follow
Jun 6
I built an AI chat app because I was tired of AI sounding like a corporate memo
#
showdev
#
ai
#
llm
#
sideprojects
1
 reaction
Comments
1
 comment
2 min read
Built an open-source memory layer for local LLMs — single-shot calls, auto-extracted constraints, no context degradation
Justin Joseph
Justin Joseph
Justin Joseph
Follow
May 2
Built an open-source memory layer for local LLMs — single-shot calls, auto-extracted constraints, no context degradation
#
showdev
#
ai
#
llm
#
opensource
Comments
Add Comment
1 min read
MAI-Thinking-1: Microsoft's New Reasoning Model and What It Means for Developers
ArshTechPro
ArshTechPro
ArshTechPro
Follow
Jun 5
MAI-Thinking-1: Microsoft's New Reasoning Model and What It Means for Developers
#
ai
#
microsoft
#
llm
#
agents
7
 reactions
Comments
1
 comment
6 min read
My agent swarm had a productive night. My pipeline lied about it.
Nic Lydon
Nic Lydon
Nic Lydon
Follow
Jun 5
My agent swarm had a productive night. My pipeline lied about it.
#
ai
#
agents
#
buildinpublic
#
llm
1
 reaction
Comments
1
 comment
5 min read
Building WeaveLLM: Why .NET Deserves a Better then LangChain
Harshil Shah
Harshil Shah
Harshil Shah
Follow
May 2
Building WeaveLLM: Why .NET Deserves a Better then LangChain
#
ai
#
dotnet
#
csharp
#
llm
Comments
Add Comment
9 min read
How LLMs Actually Work: A Developer's Mental Model
Marko Frei
Marko Frei
Marko Frei
Follow
Jun 5
How LLMs Actually Work: A Developer's Mental Model
#
ai
#
machinelearning
#
llm
#
beginners
1
 reaction
Comments
Add Comment
6 min read
What Happens When You Evaluate a B2B Sales Agent on Tasks It Was Never Designed For
Melaku Genet
Melaku Genet
Melaku Genet
Follow
May 2
What Happens When You Evaluate a B2B Sales Agent on Tasks It Was Never Designed For
#
machinelearning
#
ai
#
benchmark
#
llm
Comments
Add Comment
5 min read
Vibe Coding vs Prompt Engineering vs Context Engineering — What's the Difference?
Sreeraj Sreenivasan
Sreeraj Sreenivasan
Sreeraj Sreenivasan
Follow
Jun 5
Vibe Coding vs Prompt Engineering vs Context Engineering — What's the Difference?
#
ai
#
llm
#
programming
#
vibecoding
Comments
1
 comment
4 min read
I tested 4 free 70B-class LLM endpoints for real production work — here's what each is actually good at
Pranav Chandra
Pranav Chandra
Pranav Chandra
Follow
May 2
I tested 4 free 70B-class LLM endpoints for real production work — here's what each is actually good at
#
ai
#
llm
#
opensource
#
webdev
Comments
Add Comment
5 min read
đź‘‹
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