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
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift
chunxiaoxx
chunxiaoxx
chunxiaoxx
Follow
Jun 4
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift
#
llm
#
memory
#
mcp
#
agents
1
reaction
Comments
Add Comment
5 min read
Understanding Temperature in LLMs: The Creativity Control Knob
Vipul
Vipul
Vipul
Follow
Jun 3
Understanding Temperature in LLMs: The Creativity Control Knob
#
ai
#
beginners
#
llm
#
machinelearning
Comments
Add Comment
2 min read
I built a persistent memory graph for my Mac AI agent — here's the architecture
WAYLAND ZHANG
WAYLAND ZHANG
WAYLAND ZHANG
Follow
Jun 3
I built a persistent memory graph for my Mac AI agent — here's the architecture
#
showdev
#
ai
#
agents
#
llm
Comments
1
comment
2 min read
CLAUDE.md Compaction: Why Your Rules Disappear Mid-Session
Olivia Craft
Olivia Craft
Olivia Craft
Follow
Jun 3
CLAUDE.md Compaction: Why Your Rules Disappear Mid-Session
#
claudeai
#
aitools
#
claudemd
#
llm
Comments
Add Comment
2 min read
Sycophancy-Free Coding: How to Make AI Agents Say "No"
Luca Morricone
Luca Morricone
Luca Morricone
Follow
Jul 6
Sycophancy-Free Coding: How to Make AI Agents Say "No"
#
ai
#
llm
#
agents
#
opensource
3
reactions
Comments
10
comments
8 min read
Span attributes that catch LLM cost regressions before billing does
Jasmine Park
Jasmine Park
Jasmine Park
Follow
Jun 2
Span attributes that catch LLM cost regressions before billing does
#
observability
#
ai
#
llm
#
devops
Comments
Add Comment
1 min read
Rasengan v1.2.2 - Error overlay, LLM support & agent skills
Dilane3
Dilane3
Dilane3
Follow
Jun 3
Rasengan v1.2.2 - Error overlay, LLM support & agent skills
#
agents
#
ai
#
javascript
#
llm
Comments
Add Comment
1 min read
How to Evaluate LLM Output Quality Programmatically
Ayi NEDJIMI
Ayi NEDJIMI
Ayi NEDJIMI
Follow
Jun 16
How to Evaluate LLM Output Quality Programmatically
#
python
#
llm
#
ai
#
tutorial
1
reaction
Comments
Add Comment
5 min read
I let Claude and Codex argue about my code for a week. Here's what they caught.
Brian Mello
Brian Mello
Brian Mello
Follow
Jun 2
I let Claude and Codex argue about my code for a week. Here's what they caught.
#
ai
#
codereview
#
devtools
#
llm
Comments
Add Comment
5 min read
Claude Fable 5 is currently unavailable , here's what actually happened
Muhammad Moeed
Muhammad Moeed
Muhammad Moeed
Follow
Jun 16
Claude Fable 5 is currently unavailable , here's what actually happened
#
claude
#
ai
#
anthropic
#
llm
Comments
1
comment
2 min read
How to Cheat LLM Context: A Lightweight AI Doc Assistant Architecture
Piotr Zielinski
Piotr Zielinski
Piotr Zielinski
Follow
Jun 2
How to Cheat LLM Context: A Lightweight AI Doc Assistant Architecture
#
ai
#
architecture
#
llm
#
rag
2
reactions
Comments
Add Comment
3 min read
Lum1104 — Understand-Anything
Muhammad Shoaib Syed
Muhammad Shoaib Syed
Muhammad Shoaib Syed
Follow
Jun 2
Lum1104 — Understand-Anything
#
ai
#
llm
#
opensource
#
tooling
Comments
Add Comment
3 min read
Stop Writing Bigger Prompts. Start Writing Better Task Contracts
Balraj Singh
Balraj Singh
Balraj Singh
Follow
Jun 25
Stop Writing Bigger Prompts. Start Writing Better Task Contracts
#
ai
#
llm
#
productivity
#
softwareengineering
2
reactions
Comments
1
comment
5 min read
Hermes Agent: First Contact
Rob
Rob
Rob
Follow
Jun 2
Hermes Agent: First Contact
#
agents
#
llm
#
buildinginpublic
#
meta
Comments
Add Comment
5 min read
I kept rewriting the same quiz + spaced-repetition code. So I packaged it into an API.
limack0
limack0
limack0
Follow
Jun 2
I kept rewriting the same quiz + spaced-repetition code. So I packaged it into an API.
#
showdev
#
api
#
learning
#
llm
Comments
Add Comment
1 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