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 Your Vibe-Coded App Looks Worse Than the Showcases: A Forensic Audit
John
John
John
Follow
Jul 20
Why Your Vibe-Coded App Looks Worse Than the Showcases: A Forensic Audit
#
agents
#
ai
#
llm
#
programming
Comments
2
 comments
7 min read
I built a CLI that estimates LLM API cost before you send the request
ilan lachkar
ilan lachkar
ilan lachkar
Follow
Jul 19
I built a CLI that estimates LLM API cost before you send the request
#
showdev
#
cli
#
llm
#
opensource
Comments
Add Comment
1 min read
Building with Local LLMs: An Engineer's Approach to AI-Assisted Development
Praveen Maurya
Praveen Maurya
Praveen Maurya
Follow
Jul 18
Building with Local LLMs: An Engineer's Approach to AI-Assisted Development
#
showdev
#
ai
#
llm
#
softwareengineering
1
 reaction
Comments
Add Comment
5 min read
Deterministic serialization for multi-agent LLM sessions - 3.45x fewer tokens than JSON, up to 9.9x for non-English content
andrey-architect
andrey-architect
andrey-architect
Follow
Jul 18
Deterministic serialization for multi-agent LLM sessions - 3.45x fewer tokens than JSON, up to 9.9x for non-English content
#
showdev
#
agents
#
llm
#
performance
Comments
Add Comment
3 min read
I Built a Crew of AI Agents That Review Code Like a Real Team — Then Watched Them Argue With SigNoz
vishnu
vishnu
vishnu
Follow
Jul 18
I Built a Crew of AI Agents That Review Code Like a Real Team — Then Watched Them Argue With SigNoz
#
showdev
#
agents
#
ai
#
llm
Comments
Add Comment
4 min read
Measured: the last Sonnet update started wrapping raw JSON in a markdown fence
Model Drift Watch
Model Drift Watch
Model Drift Watch
Follow
Jul 18
Measured: the last Sonnet update started wrapping raw JSON in a markdown fence
#
llm
#
ai
#
testing
#
json
Comments
Add Comment
4 min read
Why We Treat Prompts Like Infrastructure, Not Conversations
Matt Senter
Matt Senter
Matt Senter
Follow
for
Senternet
Jul 18
Why We Treat Prompts Like Infrastructure, Not Conversations
#
ai
#
infrastructure
#
llm
#
softwareengineering
Comments
Add Comment
3 min read
Architecting lean LLM caching: how to drop a 20M-row table without losing your AI memory
Wonder-David Efe
Wonder-David Efe
Wonder-David Efe
Follow
Jul 18
Architecting lean LLM caching: how to drop a 20M-row table without losing your AI memory
#
ai
#
dataengineering
#
agents
#
llm
2
 reactions
Comments
2
 comments
4 min read
Serving Gemma 4 E2B on a TPU v6e-1: what Trillium buys, and what it doesn't
xbill
xbill
xbill
Follow
for
Google Developer Experts
Aug 11
Serving Gemma 4 E2B on a TPU v6e-1: what Trillium buys, and what it doesn't
#
tpu
#
vllm
#
llm
#
gcp
2
 reactions
Comments
Add Comment
20 min read
0.2.0: I shipped the coverage my own page had already promised
ěť´ë ą
ěť´ë ą
ěť´ë ą
Follow
Jul 18
0.2.0: I shipped the coverage my own page had already promised
#
ai
#
llm
#
security
#
python
Comments
Add Comment
7 min read
Kimi K3: The Frontier Just Went Open
Tobias Reithmeier
Tobias Reithmeier
Tobias Reithmeier
Follow
Jul 24
Kimi K3: The Frontier Just Went Open
#
ai
#
kimi
#
llm
Comments
Add Comment
7 min read
The four parts of a prompt you can actually trust
Paul Crinigan
Paul Crinigan
Paul Crinigan
Follow
Jul 19
The four parts of a prompt you can actually trust
#
ai
#
llm
#
softwaredevelopment
#
tutorial
Comments
Add Comment
1 min read
Session Pending and Memory Layers in Solon Agents: Pause Runs, Isolate History, Resume Work
Solon Framework
Solon Framework
Solon Framework
Follow
Jul 18
Session Pending and Memory Layers in Solon Agents: Pause Runs, Isolate History, Resume Work
#
agents
#
ai
#
architecture
#
llm
Comments
Add Comment
5 min read
The Server Is Fine. The Model Still Can't Use It.
Claudius
Claudius
Claudius
Follow
Aug 10
The Server Is Fine. The Model Still Can't Use It.
#
mcp
#
ai
#
testing
#
llm
1
 reaction
Comments
2
 comments
4 min read
How to Build a Good Human-in-the-Loop for Browser & Computer-Use Agents
Brenn Hill
Brenn Hill
Brenn Hill
Follow
Aug 10
How to Build a Good Human-in-the-Loop for Browser & Computer-Use Agents
#
ai
#
machinelearning
#
llm
#
programming
3
 reactions
Comments
3
 comments
8 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