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
The "AI" Badge Doesn't Measure What You Think It Does
Pascal CESCATO
Pascal CESCATO
Pascal CESCATO
Follow
Aug 15
The "AI" Badge Doesn't Measure What You Think It Does
#
discuss
#
ai
#
llm
#
writing
6
reactions
Comments
4
comments
7 min read
Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit
jamilxt
jamilxt
jamilxt
Follow
Aug 14
Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit
#
ai
#
security
#
llm
#
agents
Comments
2
comments
8 min read
Your eval suite passes. I built the tool that checks whether it checks anything.
Erik Hill
Erik Hill
Erik Hill
Follow
Aug 14
Your eval suite passes. I built the tool that checks whether it checks anything.
#
showdev
#
testing
#
llm
#
opensource
1
reaction
Comments
Add Comment
2 min read
Building a Lifeline: How I Engineered an AI Disaster Response Voice Agent in 10 Days
Ishant
Ishant
Ishant
Follow
Aug 15
Building a Lifeline: How I Engineered an AI Disaster Response Voice Agent in 10 Days
#
agents
#
ai
#
devchallenge
#
llm
Comments
Add Comment
5 min read
Sydney: Building a Hinglish AI/ML Mentor That Actually Talks — 10 Days of Voice Agents
Suyash Sahu
Suyash Sahu
Suyash Sahu
Follow
Aug 15
Sydney: Building a Hinglish AI/ML Mentor That Actually Talks — 10 Days of Voice Agents
#
agents
#
ai
#
llm
#
machinelearning
Comments
Add Comment
8 min read
Building Arogya Seva: How I Built an Ultra-Low Latency Telehealth Voice AI for Bharat in 10 Days
Viral Jethva
Viral Jethva
Viral Jethva
Follow
Aug 15
Building Arogya Seva: How I Built an Ultra-Low Latency Telehealth Voice AI for Bharat in 10 Days
#
ai
#
devchallenge
#
llm
Comments
Add Comment
5 min read
Small models where they win
INTFRAME
INTFRAME
INTFRAME
Follow
Aug 15
Small models where they win
#
ai
#
llm
#
performance
Comments
Add Comment
2 min read
Write prompts for the cache, not the reader
INTFRAME
INTFRAME
INTFRAME
Follow
Aug 15
Write prompts for the cache, not the reader
#
ai
#
llm
#
performance
Comments
Add Comment
2 min read
🦌 Mrigashira AI — Making Local AI Accessible to Everyone
Pranay Mokal
Pranay Mokal
Pranay Mokal
Follow
Aug 15
🦌 Mrigashira AI — Making Local AI Accessible to Everyone
#
ai
#
llm
#
privacy
#
software
Comments
Add Comment
2 min read
An AI Capture-the-Flag Tournament: What the Scoreboard Counted
Seth Wheeler
Seth Wheeler
Seth Wheeler
Follow
Aug 15
An AI Capture-the-Flag Tournament: What the Scoreboard Counted
#
llm
#
measurement
#
security
#
benchmarks
Comments
Add Comment
6 min read
Structured output is a contract, not a request
INTFRAME
INTFRAME
INTFRAME
Follow
Aug 15
Structured output is a contract, not a request
#
ai
#
llm
Comments
Add Comment
2 min read
Chain-of-thought: making a model think before it answers
Divyakush Punjabi
Divyakush Punjabi
Divyakush Punjabi
Follow
Aug 15
Chain-of-thought: making a model think before it answers
#
ai
#
llm
#
reasoning
#
genai
Comments
Add Comment
3 min read
Evaluating LLMs: why 'it looks good' isn't a metric
Divyakush Punjabi
Divyakush Punjabi
Divyakush Punjabi
Follow
Aug 15
Evaluating LLMs: why 'it looks good' isn't a metric
#
ai
#
llm
#
mlops
#
machinelearning
1
reaction
Comments
Add Comment
3 min read
The context window: an LLM's working memory and its limits
Divyakush Punjabi
Divyakush Punjabi
Divyakush Punjabi
Follow
Aug 15
The context window: an LLM's working memory and its limits
#
ai
#
llm
#
genai
#
machinelearning
Comments
Add Comment
3 min read
Temperature, top-p, and sampling: controlling LLM randomness
Divyakush Punjabi
Divyakush Punjabi
Divyakush Punjabi
Follow
Aug 15
Temperature, top-p, and sampling: controlling LLM randomness
#
ai
#
llm
#
genai
#
machinelearning
Comments
Add Comment
3 min read
👋
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