Skip to content
Powered by Algolia
Log in
Create account
DEV Community
#
llm
Follow
Hide
Posts
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
How Open-Source LLMs Differ: Comparing 130+ Model Architectures
amananandrai
amananandrai
amananandrai
Follow
Nov 13
How Open-Source LLMs Differ: Comparing 130+ Model Architectures
#
ai
#
llm
#
deeplearning
#
deepseek
5
reactions
Add Comment
7 min read
️🎞️ What is native multimodality?
Laurent Picard
Laurent Picard
Laurent Picard
Follow
for
Google Cloud
Nov 13
️🎞️ What is native multimodality?
#
llm
#
machinelearning
#
videos
#
justamoment
5
reactions
Add Comment
1 min read
Restricting MCP connectors to read-only access
Wojciech Wentland
Wojciech Wentland
Wojciech Wentland
Follow
Nov 13
Restricting MCP connectors to read-only access
#
mcp
#
ai
#
security
#
llm
1
reaction
2
comments
10 min read
I gave AI agents an empty API response. They made up support tickets.
Houssain El marouni
Houssain El marouni
Houssain El marouni
Follow
Nov 13
I gave AI agents an empty API response. They made up support tickets.
#
ai
#
llm
#
testing
#
opensource
Add Comment
4 min read
What app code should assume about an LLM call
Conor Bronsdon
Conor Bronsdon
Conor Bronsdon
Follow
Nov 13
What app code should assume about an LLM call
#
ai
#
llm
#
python
1
reaction
Add Comment
6 min read
Your MCP Scanner Passed. Would Your Agent Still Follow a Poisoned Tool? A Canary Method for Testing AI Agents
TechSavant Security Lab
TechSavant Security Lab
TechSavant Security Lab
Follow
Nov 13
Your MCP Scanner Passed. Would Your Agent Still Follow a Poisoned Tool? A Canary Method for Testing AI Agents
#
ai
#
security
#
mcp
#
llm
Add Comment
7 min read
Two Official Pages Disagree on When Claude Haiku 4.5 Retires
Nabil A
Nabil A
Nabil A
Follow
Nov 13
Two Official Pages Disagree on When Claude Haiku 4.5 Retires
#
ai
#
claude
#
azure
#
llm
1
comment
4 min read
Prefill vs Decode: Why Splitting Them Wins
Daniel Sam Pete Thiyagu
Daniel Sam Pete Thiyagu
Daniel Sam Pete Thiyagu
Follow
Nov 13
Prefill vs Decode: Why Splitting Them Wins
#
vllm
#
llm
#
googlecloud
#
machinelearning
1
comment
10 min read
Medindo um agente de treino: o que o few-shot fez (e não fez) com um modelo local e com o Gemini
Cibelle Rodrigues
Cibelle Rodrigues
Cibelle Rodrigues
Follow
Nov 13
Medindo um agente de treino: o que o few-shot fez (e não fez) com um modelo local e com o Gemini
#
agents
#
ai
#
llm
#
python
Add Comment
4 min read
LLM benchmark stimulus audit: 33 of 80 pairs not clean
Sunny Chokshi
Sunny Chokshi
Sunny Chokshi
Follow
Nov 13
LLM benchmark stimulus audit: 33 of 80 pairs not clean
#
security
#
llm
#
python
#
benchmark
Add Comment
4 min read
Testing LLM Tool Calls With Pytest: Asserting the Right Tool, Arguments, and Order
Mykhailo Krasnovskyi
Mykhailo Krasnovskyi
Mykhailo Krasnovskyi
Follow
Nov 13
Testing LLM Tool Calls With Pytest: Asserting the Right Tool, Arguments, and Order
#
ai
#
llm
#
testing
#
qa
Add Comment
10 min read
RLHF vs RLAIF: The Labeling Bill Behind Model Alignment
gxqwb
gxqwb
gxqwb
Follow
Nov 13
RLHF vs RLAIF: The Labeling Bill Behind Model Alignment
#
ai
#
alignment
#
training
#
llm
Add Comment
5 min read
An AI agent believes whatever its tools send back
Ravi Prakash meena
Ravi Prakash meena
Ravi Prakash meena
Follow
Nov 13
An AI agent believes whatever its tools send back
#
agents
#
ai
#
llm
#
mcp
2
reactions
3
comments
6 min read
Ripple 65B Puts Open Coding Models to a More Practical Test
Jaromir Tesar
Jaromir Tesar
Jaromir Tesar
Follow
Nov 13
Ripple 65B Puts Open Coding Models to a More Practical Test
#
ai
#
coding
#
llm
#
opensource
Add Comment
8 min read
One constant was costing my schema retriever 17 points
Ashish sinha
Ashish sinha
Ashish sinha
Follow
Nov 13
One constant was costing my schema retriever 17 points
#
ai
#
database
#
llm
#
sql
Add Comment
2 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
‹
›
⌂
移動
⧉
↓
×
≡