DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Anthropic Drops Claude Sonnet 4.5: Extended Thinking Hits 200K Context for Agentic Coding
unfiltered_anshul profile

Anthropic Drops Claude Sonnet 4.5: Extended Thinking Hits 200K Context for Agentic Coding

#agents #ai #claude #llm
1
Comments
3 min read
Automation Bias: Why People Rubber-Stamp AI (and How to Fix It)
brennhill profile

Automation Bias: Why People Rubber-Stamp AI (and How to Fix It)

#ai #machinelearning #llm #programming
1
Comments
7 min read
Mistral Small 3.2 Lands With Sharper Function Calling and a 128K Context Window
unfiltered_anshul profile

Mistral Small 3.2 Lands With Sharper Function Calling and a 128K Context Window

#ai #llm #opensource
1
Comments
4 min read
Building a Repository Intelligence Layer for AI Coding Agents
mustafizur_rahman_dc9d3e6 profile

Building a Repository Intelligence Layer for AI Coding Agents

#agents #ai #llm #softwareengineering
Comments
3 min read
The Autonomy Paradox: When an AI Agent Can't Follow Its Own Rules
wharsojo profile

The Autonomy Paradox: When an AI Agent Can't Follow Its Own Rules

#agents #ai #automation #llm
Comments
6 min read
Did FP8 make the model dumber? A per-prompt regression check for quantized serving
conatusai profile
Jahn

Did FP8 make the model dumber? A per-prompt regression check for quantized serving

#llm #machinelearning #performance #python
Comments
3 min read
I Thought the Optimizer Was the Product. I Was Wrong. The Gate Was.
debashish_ghosal profile

I Thought the Optimizer Was the Product. I Was Wrong. The Gate Was.

#healthydebate #ai #llm #testing
9
Comments 4
5 min read
Las nuevas reglas del "context engineering" para los modelos Claude 5
victoraguilarc profile

Las nuevas reglas del "context engineering" para los modelos Claude 5

#ai #claude #llm
Comments 1
7 min read
10,000 Agents, Zero Tokens: Why the Best AI Architectures "Skip" the LLM
alisterbaroi profile

10,000 Agents, Zero Tokens: Why the Best AI Architectures "Skip" the LLM

#ai #mcp #llm #security
6
Comments 5
5 min read
How We Built Perceive: Web Content Extraction for RAG Pipelines
thephoenix229 profile

How We Built Perceive: Web Content Extraction for RAG Pipelines

#ai #llm #rag #webscraping
Comments 1
8 min read
A delegate cannot write, present, or invoke other delegates. I ran that sentence as authority.
rafael_asor profile

A delegate cannot write, present, or invoke other delegates. I ran that sentence as authority.

#security #ai #llm #anthropic
Comments
10 min read
GPT-6 Astra vs Fable 5.1 vs Gemini 3.8 Flash: The Ultimate Comparison
gabrielanhaia profile

GPT-6 Astra vs Fable 5.1 vs Gemini 3.8 Flash: The Ultimate Comparison

#ai #llm #openai #google
8
Comments
8 min read
I Tried 4 Models to Save My Self-Improving Agent. All 4 Failed.
debashish_ghosal profile

I Tried 4 Models to Save My Self-Improving Agent. All 4 Failed.

#healthydebate #ai #llm #agents
24
Comments 2
7 min read
The delegate your agent trusts by shape
rafael_asor profile

The delegate your agent trusts by shape

#ai #security #llm #anthropic
Comments
3 min read
Fable 5.1 cut cache reads by 75%. Cost per task went up 20% anyway.
aidiveyt profile

Fable 5.1 cut cache reads by 75%. Cost per task went up 20% anyway.

#discuss #ai #claude #llm
1
Comments 4
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.