DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Thermodynamic Continual Learning in Persistent AI Agents (110+ Days Runtime)
nilegreen profile

Thermodynamic Continual Learning in Persistent AI Agents (110+ Days Runtime)

#ai #machinelearning #llm #architecture
Comments
2 min read
Dogfooding an LLM agent eval pack on my own production agent — what 6-dim methodology surfaced
weiseer profile

Dogfooding an LLM agent eval pack on my own production agent — what 6-dim methodology surfaced

#ai #llm #agents #evaluation
Comments 1
5 min read
Making an LLM "get tired" of bad conversation: the engagement-budget prompt
matanellhayani profile

Making an LLM "get tired" of bad conversation: the engagement-budget prompt

#llm #ai #prompt #webdev
Comments
3 min read
How Superpowers Forces Skill Execution
sonim1 profile

How Superpowers Forces Skill Execution

#agents #ai #cli #llm
Comments 3
7 min read
How I Escaped Claude & Cursor Limits: The Ultimate Free Local AI Coding Setup with Ollama + Continue.dev (2026 Guide)
david_bilsonn profile

How I Escaped Claude & Cursor Limits: The Ultimate Free Local AI Coding Setup with Ollama + Continue.dev (2026 Guide)

#ai #vscode #llm #programming
6
Comments 2
4 min read
Stop Building AI Wrappers. Start Building AI Products.
mzunain profile

Stop Building AI Wrappers. Start Building AI Products.

#ai #llm #webdev #programming
1
Comments
2 min read
What an AI does when nobody on the line is human (two case studies)
michael_trifonov_0cb74f99 profile

What an AI does when nobody on the line is human (two case studies)

#discuss #ai #llm #agents
2
Comments
7 min read
The model was never the problem. The context was
kevinluddy39 profile

The model was never the problem. The context was

#ai #llm #opensource #observability
Comments
5 min read
We Asked 10 LLMs to Write Efficient Code. Only 4 Got Better.
vystartasv profile

We Asked 10 LLMs to Write Efficient Code. Only 4 Got Better.

#ai #llm #benchmark #programming
Comments
5 min read
10 Models Tested: From 81.6% to 10%. The Free Tier is a Full-On Gamble.
vystartasv profile

10 Models Tested: From 81.6% to 10%. The Free Tier is a Full-On Gamble.

#ai #agents #benchmark #llm
Comments
4 min read
Qwen 3.6 27B Arrives with GGUF, llama.cpp Powers Local Multimodal
soytuber profile
soy

Qwen 3.6 27B Arrives with GGUF, llama.cpp Powers Local Multimodal

#ai #llm #selfhosted
Comments
4 min read
The Representation Problem: Why RAG vs. Agentic Search Is the Wrong Debate
chen115y profile

The Representation Problem: Why RAG vs. Agentic Search Is the Wrong Debate

#rag #ai #llm #architecture
Comments 1
17 min read
Lovable's 48-Day Silent Breach Shows Why AI Platforms Need Audit Trails, Not Just Bug Bounties
lkelly profile
Logan for Waxell

Lovable's 48-Day Silent Breach Shows Why AI Platforms Need Audit Trails, Not Just Bug Bounties

#lovable #ai #security #llm
Comments
9 min read
MCP is quietly commoditizing data+model SaaS moats — the structural case
connerlambden profile

MCP is quietly commoditizing data+model SaaS moats — the structural case

#ai #llm #mcp #saas
Comments
5 min read
The 2026 Chinese LLM Price War: Top 5 Frontier API Costs Compared
hassann profile

The 2026 Chinese LLM Price War: Top 5 Frontier API Costs Compared

#news #ai #api #llm
1
Comments
11 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.