Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Claude Code Source Analysis Series, Chapter 4: Context Management
LienJack
LienJack
LienJack
Follow
May 10
Claude Code Source Analysis Series, Chapter 4: Context Management
#
agents
#
architecture
#
claude
#
llm
Comments
Add Comment
16 min read
Claude Code Source Analysis Series, Chapter 3: Prompt Construction
LienJack
LienJack
LienJack
Follow
May 10
Claude Code Source Analysis Series, Chapter 3: Prompt Construction
#
agents
#
ai
#
claude
#
llm
Comments
Add Comment
16 min read
A pergunta errada Ă©: "Qual Ă© a melhor LLM?"
Camila Rody
Camila Rody
Camila Rody
Follow
Jun 2
A pergunta errada Ă©: "Qual Ă© a melhor LLM?"
#
ai
#
llm
#
webdev
#
programming
Comments
Add Comment
3 min read
Anthropic Was Right About One Thing: Broad Safety Decisions Are Dangerous
Gen.Y.Sakai
Gen.Y.Sakai
Gen.Y.Sakai
Follow
Jun 13
Anthropic Was Right About One Thing: Broad Safety Decisions Are Dangerous
#
ai
#
llm
#
programming
#
claude
Comments
Add Comment
42 min read
Trace Sampling for LLM Apps: Keep the Spans That Matter, Drop the Rest
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Trace Sampling for LLM Apps: Keep the Spans That Matter, Drop the Rest
#
ai
#
observability
#
llm
#
devops
Comments
1
 comment
6 min read
TTFT vs Total Latency: Instrumenting What Users Actually Feel
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
TTFT vs Total Latency: Instrumenting What Users Actually Feel
#
llm
#
observability
#
devops
#
tutorial
Comments
Add Comment
6 min read
Temperature vs top-p: Which Knob to Turn and When
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Temperature vs top-p: Which Knob to Turn and When
#
llm
#
ai
#
prompt
#
tutorial
Comments
Add Comment
6 min read
Few-Shot or Fine-Tune in 2026: The Decision Most Teams Get Backwards
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Few-Shot or Fine-Tune in 2026: The Decision Most Teams Get Backwards
#
ai
#
llm
#
promptengineering
#
machinelearning
Comments
Add Comment
6 min read
JSON or XML Tags for LLM Output: The Format That Holds Under Pressure
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
JSON or XML Tags for LLM Output: The Format That Holds Under Pressure
#
llm
#
ai
#
prompt
#
json
Comments
1
 comment
6 min read
Online vs Offline Evals: Where Each One Catches the Bug
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Online vs Offline Evals: Where Each One Catches the Bug
#
llm
#
observability
#
evals
#
ai
Comments
Add Comment
6 min read
An LLM Error Taxonomy: Classifying Failures in Your Traces
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
An LLM Error Taxonomy: Classifying Failures in Your Traces
#
llm
#
observability
#
devops
#
tutorial
Comments
Add Comment
6 min read
Delimiters as Defense: Structuring Prompts Against Injection
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Delimiters as Defense: Structuring Prompts Against Injection
#
ai
#
llm
#
security
#
prompt
Comments
Add Comment
5 min read
BM25 + Dense Fusion: When Keyword Search Saves Your RAG
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
BM25 + Dense Fusion: When Keyword Search Saves Your RAG
#
rag
#
ai
#
llm
#
search
Comments
Add Comment
7 min read
ReAct vs Plan-and-Execute: Picking an Agent Loop in 2026
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
ReAct vs Plan-and-Execute: Picking an Agent Loop in 2026
#
ai
#
agents
#
llm
#
architecture
Comments
Add Comment
6 min read
Context-Window Eviction: What to Drop When the Agent Fills Up
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Context-Window Eviction: What to Drop When the Agent Fills Up
#
ai
#
agents
#
python
#
llm
Comments
Add Comment
6 min read
đź‘‹
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