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
One Leg Can Raise an Objection. It Can't Settle One.
John
John
John
Follow
Aug 13
One Leg Can Raise an Objection. It Can't Settle One.
#
agents
#
ai
#
automation
#
llm
Comments
10
 comments
6 min read
I Gave DeepSeek a Token Limit. It Ignored Me.
Haoxiang Li
Haoxiang Li
Haoxiang Li
Follow
Aug 14
I Gave DeepSeek a Token Limit. It Ignored Me.
#
ai
#
llm
#
api
#
deepseek
2
 reactions
Comments
2
 comments
7 min read
I measured the RAG technique menu on 46,000 chunks. Four things mattered.
Lev Riabov
Lev Riabov
Lev Riabov
Follow
Aug 2
I measured the RAG technique menu on 46,000 chunks. Four things mattered.
#
ai
#
llm
#
rag
#
search
1
 reaction
Comments
6
 comments
11 min read
LLM Latency Budget: Make AI Workflows Feel Fast Without Guessing
Jack M
Jack M
Jack M
Follow
Jul 15
LLM Latency Budget: Make AI Workflows Feel Fast Without Guessing
#
ai
#
llm
#
performance
#
ux
2
 reactions
Comments
1
 comment
9 min read
The Bug Was in the Brief, Upstream of Both Reviews
John
John
John
Follow
Aug 14
The Bug Was in the Brief, Upstream of Both Reviews
#
agents
#
ai
#
llm
#
writing
1
 reaction
Comments
2
 comments
7 min read
Large-Scale Code Migration Workflows Powered by Claude Code
Tidiane Stano
Tidiane Stano
Tidiane Stano
Follow
Aug 3
Large-Scale Code Migration Workflows Powered by Claude Code
#
ai
#
claude
#
llm
#
softwareengineering
Comments
Add Comment
7 min read
What Differentiates GPT-5.6 from GPT-5.5? Five Critical Points Developers Should Prioritize
Tidiane Stano
Tidiane Stano
Tidiane Stano
Follow
Aug 3
What Differentiates GPT-5.6 from GPT-5.5? Five Critical Points Developers Should Prioritize
#
ai
#
llm
#
openai
#
softwareengineering
Comments
Add Comment
4 min read
Making a Bloated Claude Code Fast Again: Auditing Context Injection Down From 228KB to 48KB
Lily
Lily
Lily
Follow
Jul 11
Making a Bloated Claude Code Fast Again: Auditing Context Injection Down From 228KB to 48KB
#
claudecode
#
ai
#
productivity
#
llm
Comments
1
 comment
4 min read
Stop writing MCP tool descriptions like a human is reading them
Renato Marinho
Renato Marinho
Renato Marinho
Follow
Aug 3
Stop writing MCP tool descriptions like a human is reading them
#
mcp
#
ai
#
llm
#
programming
2
 reactions
Comments
2
 comments
4 min read
LLM Model Selection Matrix: Pick the Cheapest Reliable Model for Each Feature
Jack M
Jack M
Jack M
Follow
Aug 14
LLM Model Selection Matrix: Pick the Cheapest Reliable Model for Each Feature
#
ai
#
saas
#
llm
#
devops
2
 reactions
Comments
2
 comments
9 min read
E‑‑: The middle ground between English and Python
Oded Fuhrmann
Oded Fuhrmann
Oded Fuhrmann
Follow
Jul 10
E‑‑: The middle ground between English and Python
#
python
#
llm
#
programming
#
opensource
Comments
Add Comment
6 min read
What I Learned Cutting Claude Code's Token Bill by 77%
rguiu
rguiu
rguiu
Follow
Jul 12
What I Learned Cutting Claude Code's Token Bill by 77%
#
ai
#
llm
#
opensource
#
claude
4
 reactions
Comments
1
 comment
5 min read
Why Enterprise AI Requires Smarter Orchestration, Not Bigger Models
Oba J. Alege
Oba J. Alege
Oba J. Alege
Follow
Jul 24
Why Enterprise AI Requires Smarter Orchestration, Not Bigger Models
#
ai
#
architecture
#
llm
#
systemdesign
1
 reaction
Comments
Add Comment
1 min read
How I replaced LLM calls with coding agent calls and saved money
popiol
popiol
popiol
Follow
Jul 10
How I replaced LLM calls with coding agent calls and saved money
#
agents
#
ai
#
llm
#
programming
Comments
Add Comment
3 min read
Don't Let the AI Find Your Bugs. Let It Judge Them.
Ali Afana
Ali Afana
Ali Afana
Follow
Aug 13
Don't Let the AI Find Your Bugs. Let It Judge Them.
#
ai
#
security
#
java
#
llm
21
 reactions
Comments
4
 comments
9 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