DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
If models get smarter, why does the same task cost more?
bickov profile

If models get smarter, why does the same task cost more?

#ai #llm #webdev #productivity
Comments 1
2 min read
GPT-6 Astra vs GPT-5.6 Sol: Choosing by Completed Work, Not Model Age
ryancole1 profile

GPT-6 Astra vs GPT-5.6 Sol: Choosing by Completed Work, Not Model Age

#ai #agents #llm
Comments
10 min read
How AI Models “Remember” You Across Different Chats
melchizedek_madaki_a0fdb0 profile

How AI Models “Remember” You Across Different Chats

#ai #chatgpt #claude #llm
2
Comments
2 min read
Context length cost for .NET developers: Why your prompts are draining the budget
amitesh0512 profile

Context length cost for .NET developers: Why your prompts are draining the budget

#llm #net #azureopenai #promptengineering
Comments
7 min read
Looking for honest reviewers I wrote a book on building local AI apps with Ollama
embededsystemguyyyyy profile

Looking for honest reviewers I wrote a book on building local AI apps with Ollama

#ai #python #ollama #llm
Comments
1 min read
How a Single AI Agent Replaced a 5-Person Data Team at a Fintech Startup
aibughunter profile

How a Single AI Agent Replaced a 5-Person Data Team at a Fintech Startup

#aiagents #ai #llm #webdev
Comments
4 min read
How to Catch and Replay Production Agent Failures: Trace-Native CI/CD in Practice
priyeshdave6 profile

How to Catch and Replay Production Agent Failures: Trace-Native CI/CD in Practice

#ai #agenticai #machinelearning #llm
Comments 1
4 min read
Your agent's confirm token is one-shot. Your write still happens twice.
vanhpoker profile

Your agent's confirm token is one-shot. Your write still happens twice.

#ai #security #llm #architecture
2
Comments 6
5 min read
From 51% to 90.5%: fine-tuning a local triage model on 10,003 support tickets (open source and measured)
gjusev profile
gj0xv

From 51% to 90.5%: fine-tuning a local triage model on 10,003 support tickets (open source and measured)

#ai #llm #machinelearning #python
2
Comments 6
3 min read
How we made 2,000 customer conversations queryable in a few hours
israel_vsquez profile

How we made 2,000 customer conversations queryable in a few hours

#ai #architecture #aws #llm
Comments
3 min read
What Memory API Feature Would Make You Think "Okay, I'd Actually Try That"?
woochan profile

What Memory API Feature Would Make You Think "Okay, I'd Actually Try That"?

#discuss #ai #api #llm
6
Comments
1 min read
A 404 is the easy half. Scoring a package that actually exists is where we got it wrong.
jj1423 profile
jj1423

A 404 is the easy half. Scoring a package that actually exists is where we got it wrong.

#agents #cybersecurity #llm #security
2
Comments 6
5 min read
How 8-bit quantization shrinks an LLM to half of its size — and why a single outlier weight can quietly ruin it
susheem-k profile

How 8-bit quantization shrinks an LLM to half of its size — and why a single outlier weight can quietly ruin it

#ai #llm #machinelearning #python
9
Comments 9
11 min read
Kimi K3: The 2.8 Trillion Parameter AI Model That's Changing Everything
ryan_zhao profile

Kimi K3: The 2.8 Trillion Parameter AI Model That's Changing Everything

#ai #kimi #llm #programming
Comments 1
2 min read
Fine-Tune, Deploy and Use LLM As AI Agent
joxiahdev profile

Fine-Tune, Deploy and Use LLM As AI Agent

#llm #ai #finetuning #agents
Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.