DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why RAG Pipelines Silently Hallucinate — And The Decay Score That Catches It Before The LLM Does
vlsiddarth profile

Why RAG Pipelines Silently Hallucinate — And The Decay Score That Catches It Before The LLM Does

#rag #llm #machinelearning #python
Comments
2 min read
Two architectures that didn't help small-model agent memory on a free T4
atty57 profile

Two architectures that didn't help small-model agent memory on a free T4

#machinelearning #ai #python #llm
Comments
12 min read
Is That Really 'a'? How Homoglyph Attacks Bypass LLM Security Filters (with Python examples)
dokasuka_don_de7635cc481c profile

Is That Really 'a'? How Homoglyph Attacks Bypass LLM Security Filters (with Python examples)

#security #python #llm #unicode
Comments
6 min read
How Thinking Machines built interactivity into the model
thousand_miles_ai profile

How Thinking Machines built interactivity into the model

#news #ai #llm #machinelearning
Comments
4 min read
qwen2.5-coder is too slow for Claude Code on a Mac. Here's the fix.
malik_chohra profile

qwen2.5-coder is too slow for Claude Code on a Mac. Here's the fix.

#claudecode #ollama #ai #llm
Comments 7
8 min read
How ChatGPT Works (Simple Explanation for Beginners)
debugdiariesbyswethap profile

How ChatGPT Works (Simple Explanation for Beginners)

#ai #machinelearning #chatgpt #llm
Comments
2 min read
LLM Gateway Explained — Build One With LiteLLM + LangChain
learningwithmainsh profile

LLM Gateway Explained — Build One With LiteLLM + LangChain

#ai #architecture #llm #tutorial
1
Comments
5 min read
When Your LLM Provider Pulls the Rug: Lessons from Anthropic's OAuth Shutdown
claire_nguyen profile

When Your LLM Provider Pulls the Rug: Lessons from Anthropic's OAuth Shutdown

#llm
Comments
2 min read
2026 Q1 is the year developers still build the agent harness. 2026 Q3 / 2027 is the year the LLM builds its own harness.
programming_withjackche profile

2026 Q1 is the year developers still build the agent harness. 2026 Q3 / 2027 is the year the LLM builds its own harness.

#agents #ai #llm #tooling
Comments 1
4 min read
Stop prompting "write me an API" — teach the LLM the shape first
rlabs profile

Stop prompting "write me an API" — teach the LLM the shape first

#showdev #ai #llm #tutorial
Comments
2 min read
From Tokens to Attention: My First Real Mental Model of LLMs
upayanghosh profile

From Tokens to Attention: My First Real Mental Model of LLMs

#ai #beginners #llm #machinelearning
1
Comments 2
5 min read
Why Much AI Memory Risks Rotting — The Exception Is the Memory of Being Wrong
kenielzep97 profile

Why Much AI Memory Risks Rotting — The Exception Is the Memory of Being Wrong

#ai #llm #agents #productivity
Comments
11 min read
What I Learned Building with Gemma 4

Gemma 4 Challenge: Write about Gemma 4 Submission
allan_kipruto_7f71bb911c6 profile

What I Learned Building with Gemma 4

#devchallenge #gemmachallenge #gemma #llm
3
Comments
4 min read
Chunk Overlap: The RAG Parameter Most Teams Pick Wrong
gabrielanhaia profile

Chunk Overlap: The RAG Parameter Most Teams Pick Wrong

#rag #ai #llm #python
Comments
7 min read
Reranker Selection: Cross-Encoder vs LLM-as-Reranker vs ColBERT: Which Earns Its Latency
gabrielanhaia profile

Reranker Selection: Cross-Encoder vs LLM-as-Reranker vs ColBERT: Which Earns Its Latency

#rag #ai #llm #benchmark
Comments
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.