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
Search Didn't Make Your LLM Dumber. Unweighted Context Did.
YuhaoLin2005
YuhaoLin2005
YuhaoLin2005
Follow
Jun 29
Search Didn't Make Your LLM Dumber. Unweighted Context Did.
#
ai
#
llm
#
mcp
#
agents
1
 reaction
Comments
15
 comments
3 min read
Evaluating Agents With an LLM-as-Judge Harness (Without Kidding Yourself About It)
Virginia Nyambura Mwega
Virginia Nyambura Mwega
Virginia Nyambura Mwega
Follow
Jul 1
Evaluating Agents With an LLM-as-Judge Harness (Without Kidding Yourself About It)
#
llm
#
systemdesign
#
testing
#
webdev
Comments
2
 comments
5 min read
Stop letting Claude guess your SaaS API auth flow
michielinksee
michielinksee
michielinksee
Follow
Jul 1
Stop letting Claude guess your SaaS API auth flow
#
api
#
claude
#
llm
#
saas
7
 reactions
Comments
1
 comment
5 min read
llms.txt and GEO in 2026: How to Get Your Site Cited by AI Search
Mohammed Banani
Mohammed Banani
Mohammed Banani
Follow
Jun 2
llms.txt and GEO in 2026: How to Get Your Site Cited by AI Search
#
seo
#
llm
#
ai
#
web
Comments
1
 comment
9 min read
I built 3 free APIs for LLM developers — here's what I shipped and why
David | Kordhub
David | Kordhub
David | Kordhub
Follow
Jul 1
I built 3 free APIs for LLM developers — here's what I shipped and why
#
api
#
webdev
#
llm
#
opensource
Comments
Add Comment
2 min read
Generative AI: What Happens When You Type a Prompt?
Mohammad Mahabub Alam
Mohammad Mahabub Alam
Mohammad Mahabub Alam
Follow
Jul 1
Generative AI: What Happens When You Type a Prompt?
#
ai
#
javascript
#
llm
#
machinelearning
2
 reactions
Comments
Add Comment
6 min read
We Measured LLM Prompt Caching in Production — Same Prompt, 0% to 91% Hit Rates
sm1ck
sm1ck
sm1ck
Follow
May 28
We Measured LLM Prompt Caching in Production — Same Prompt, 0% to 91% Hit Rates
#
ai
#
python
#
llm
#
performance
Comments
Add Comment
5 min read
What Is Lua AI? A Developer's Guide to Building AI Agents
Ladipo Samuel
Ladipo Samuel
Ladipo Samuel
Follow
Jul 1
What Is Lua AI? A Developer's Guide to Building AI Agents
#
agents
#
ai
#
llm
#
programming
2
 reactions
Comments
Add Comment
3 min read
Stop hand-parsing LLM JSON: structured outputs with pydantic-ai
Wade Allen
Wade Allen
Wade Allen
Follow
Jun 20
Stop hand-parsing LLM JSON: structured outputs with pydantic-ai
#
python
#
ai
#
pydantic
#
llm
2
 reactions
Comments
1
 comment
2 min read
I stopped prompting my agent. Now I design the loop that prompts it.
Sébastien Conejo
Sébastien Conejo
Sébastien Conejo
Follow
Jun 30
I stopped prompting my agent. Now I design the loop that prompts it.
#
ai
#
agents
#
llm
#
opensource
8
 reactions
Comments
3
 comments
5 min read
The End of AI "Slop"? How Google is Using LoRA and LLMs to Fight Coordinated Synthetic Spam
Sensei
Sensei
Sensei
Follow
Jul 1
The End of AI "Slop"? How Google is Using LoRA and LLMs to Fight Coordinated Synthetic Spam
#
ai
#
cybersecurity
#
google
#
llm
1
 reaction
Comments
Add Comment
5 min read
OWASP LLM Top 10 in Production: How I Audited My TypeScript Agent Pipeline Against All 10 Risks — and What I Found
Juan Torchia
Juan Torchia
Juan Torchia
Follow
Jun 20
OWASP LLM Top 10 in Production: How I Audited My TypeScript Agent Pipeline Against All 10 Risks — and What I Found
#
english
#
typescript
#
llm
#
seguridad
1
 reaction
Comments
Add Comment
9 min read
/align v0.8 — personal evals for Claude Code, maintained by an LLM agent
Agent Ggrigo
Agent Ggrigo
Agent Ggrigo
Follow
May 28
/align v0.8 — personal evals for Claude Code, maintained by an LLM agent
#
ai
#
productivity
#
claude
#
llm
Comments
1
 comment
4 min read
Notes: Memory, Context, and Large Language Models (LLMs)
Vladimir Panov
Vladimir Panov
Vladimir Panov
Follow
Jul 1
Notes: Memory, Context, and Large Language Models (LLMs)
#
llm
#
ai
#
memory
4
 reactions
Comments
1
 comment
9 min read
Tracking token usage across OpenAI, Anthropic, and Gemini: every streaming gotcha I hit
SPANLENS
SPANLENS
SPANLENS
Follow
Jun 20
Tracking token usage across OpenAI, Anthropic, and Gemini: every streaming gotcha I hit
#
ai
#
llm
#
opensource
#
typescript
Comments
1
 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