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
Picking a Gemma 4 Quantization: VRAM Math That Actually Matters
ethanlin
ethanlin
ethanlin
Follow
Jul 24
Picking a Gemma 4 Quantization: VRAM Math That Actually Matters
#
llm
#
opensource
#
machinelearning
#
python
1
reaction
Comments
Add Comment
2 min read
بارامتر الجهد لكلود أوبوس 5: مقايضة التكلفة مقابل القدرة
Yusuf Khalidd
Yusuf Khalidd
Yusuf Khalidd
Follow
Jul 25
بارامتر الجهد لكلود أوبوس 5: مقايضة التكلفة مقابل القدرة
#
ai
#
api
#
claude
#
llm
Comments
Add Comment
3 min read
Parâmetro de Esforço do Claude Opus 5: Trocando Custo por Capacidade
Lucas
Lucas
Lucas
Follow
Jul 25
Parâmetro de Esforço do Claude Opus 5: Trocando Custo por Capacidade
#
ai
#
api
#
claude
#
llm
Comments
Add Comment
10 min read
Making a launch video for Claude Opus 5
Remocn
Remocn
Remocn
Follow
Jul 24
Making a launch video for Claude Opus 5
#
ai
#
claude
#
llm
#
marketing
Comments
Add Comment
7 min read
Why Your Multi-Agent AI System Keeps Getting Stuck in Infinite Loops (And How We Fixed It)
Shahdin Salman
Shahdin Salman
Shahdin Salman
Follow
Jul 24
Why Your Multi-Agent AI System Keeps Getting Stuck in Infinite Loops (And How We Fixed It)
#
agents
#
ai
#
architecture
#
llm
Comments
1
comment
3 min read
Your Prompt Templates Are Tool Calls: How AskUserQuestion's 4-Option Cap Bit Me Three Times
Wessam Ibrahim
Wessam Ibrahim
Wessam Ibrahim
Follow
Jul 24
Your Prompt Templates Are Tool Calls: How AskUserQuestion's 4-Option Cap Bit Me Three Times
#
claude
#
ai
#
llm
#
agents
5
reactions
Comments
1
comment
4 min read
The Watermelon Effect: How My AI Scored 94% in Testing But Only 22.2% in Real Use
Kumar Swamy
Kumar Swamy
Kumar Swamy
Follow
Jul 24
The Watermelon Effect: How My AI Scored 94% in Testing But Only 22.2% in Real Use
#
ai
#
llm
#
rag
#
testing
Comments
Add Comment
6 min read
Qwen2 is here. It’s time to re-evaluate your default model choices.
albe_sf
albe_sf
albe_sf
Follow
Jul 24
Qwen2 is here. It’s time to re-evaluate your default model choices.
#
ai
#
llm
#
opensource
#
machinelearning
Comments
Add Comment
3 min read
JSON Schema Doesn't Prevent AI Hallucinations (And That's Okay)
Hardik Mehta
Hardik Mehta
Hardik Mehta
Follow
Jul 24
JSON Schema Doesn't Prevent AI Hallucinations (And That's Okay)
#
ai
#
llm
#
openai
Comments
Add Comment
3 min read
Your eval's confidence interval assumes independent examples. Yours are clustered.
Maya Andersson
Maya Andersson
Maya Andersson
Follow
Jul 28
Your eval's confidence interval assumes independent examples. Yours are clustered.
#
statistics
#
llm
#
datascience
#
testing
2
reactions
Comments
Add Comment
4 min read
How I Let a Cloud AI Operate My Home Without Handing Over My Home
Nova
Nova
Nova
Follow
Jul 28
How I Let a Cloud AI Operate My Home Without Handing Over My Home
#
ai
#
privacy
#
selfhosted
#
llm
3
reactions
Comments
Add Comment
3 min read
The AI Wasn't Hallucinating. Our Architecture Was.
Hardik Mehta
Hardik Mehta
Hardik Mehta
Follow
Jul 24
The AI Wasn't Hallucinating. Our Architecture Was.
#
ai
#
architecture
#
llm
#
softwareengineering
Comments
Add Comment
2 min read
How to run Hermes, a self-improving personal AI agent, fully local with QVAC
Thomas
Thomas
Thomas
Follow
for
QVAC by Tether
Jul 24
How to run Hermes, a self-improving personal AI agent, fully local with QVAC
#
hermes
#
ai
#
llm
#
agents
Comments
Add Comment
7 min read
Blocking an AI agent's tool call before it runs: runtime verification with LTL3
Purav Kanda
Purav Kanda
Purav Kanda
Follow
Aug 6
Blocking an AI agent's tool call before it runs: runtime verification with LTL3
#
agents
#
ai
#
llm
#
security
Comments
1
comment
4 min read
Dead-Letter Queues for LLM Extraction Failures: Capture, Triage, and Replay Without Losing Trust
Hitarth Desai
Hitarth Desai
Hitarth Desai
Follow
Jul 24
Dead-Letter Queues for LLM Extraction Failures: Capture, Triage, and Replay Without Losing Trust
#
llm
#
ai
#
opensource
1
reaction
Comments
Add Comment
6 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