Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
evals
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Our AI forecast lost to 'nothing changes'. Here is the test we now run on every forecast
iloblique
iloblique
iloblique
Follow
Nov 18
Our AI forecast lost to 'nothing changes'. Here is the test we now run on every forecast
#
aiforecasting
#
evals
#
dataquality
#
reintelligence
Comments
Add Comment
6 min read
Moderation
Hy4 Flash walkthrough is up: what 1/20 the cost and half the coding score actually looks like on screen
InApp
InApp
InApp
Follow
Nov 18
Hy4 Flash walkthrough is up: what 1/20 the cost and half the coding score actually looks like on screen
#
llm
#
evals
#
walkthrough
#
ai
1
 reaction
Comments
Add Comment
2 min read
Moderation
Your AI Model Is Not a Dependency Pin: Build an Eval Gate for Model Churn
jamilxt
jamilxt
jamilxt
Follow
Nov 17
Your AI Model Is Not a Dependency Pin: Build an Eval Gate for Model Churn
#
ai
#
llm
#
evals
#
architecture
2
 reactions
Comments
Add Comment
8 min read
Moderation
LLM-as-judge evals: writing the rubric, and the failure modes that lie to you
Shipwright
Shipwright
Shipwright
Follow
Nov 15
LLM-as-judge evals: writing the rubric, and the failure modes that lie to you
#
evals
#
llmjudge
#
claude
#
testing
Comments
Add Comment
3 min read
Moderation
Run your own bake-off before you pick a production model
Conor Bronsdon
Conor Bronsdon
Conor Bronsdon
Follow
Nov 14
Run your own bake-off before you pick a production model
#
ai
#
llm
#
evals
#
performance
Comments
Add Comment
4 min read
Moderation
Showing my work: the four artifacts behind an AI judge for generated courses (part 1)
Antonio Scotland
Antonio Scotland
Antonio Scotland
Follow
Nov 18
Showing my work: the four artifacts behind an AI judge for generated courses (part 1)
#
evals
#
llm
#
agents
#
edtech
2
 reactions
Comments
1
 comment
8 min read
Moderation
"Trust Me Bro" Benchmarks — How AI Labs Grade Their Own Homework
Sankar
Sankar
Sankar
Follow
Nov 14
"Trust Me Bro" Benchmarks — How AI Labs Grade Their Own Homework
#
ai
#
llm
#
benchmarks
#
evals
Comments
Add Comment
29 min read
Moderation
MCP structuredContent: Claude Code Drops Your Text Blocks
Jeremy Longshore
Jeremy Longshore
Jeremy Longshore
Follow
Nov 14
MCP structuredContent: Claude Code Drops Your Text Blocks
#
mcp
#
claudecode
#
evals
#
aiagents
1
 reaction
Comments
2
 comments
9 min read
Moderation
Why an 88.64 leaderboard score needed the catch in the same sentence
InApp
InApp
InApp
Follow
Nov 8
Why an 88.64 leaderboard score needed the catch in the same sentence
#
benchmarks
#
evals
#
video
#
ai
Comments
Add Comment
1 min read
Moderation
Home-made Evals Just Taste Better
Konstantin Gredeskoul
Konstantin Gredeskoul
Konstantin Gredeskoul
Follow
Nov 5
Home-made Evals Just Taste Better
#
evals
#
ai
#
ruby
#
opensource
3
 reactions
Comments
Add Comment
8 min read
Moderation
The Eval Scorers You Actually Need for LLM Apps (and When to Use Each)
Royal Simpson Pinto
Royal Simpson Pinto
Royal Simpson Pinto
Follow
Nov 10
The Eval Scorers You Actually Need for LLM Apps (and When to Use Each)
#
ai
#
testing
#
llm
#
evals
1
 reaction
Comments
Add Comment
5 min read
Moderation
Catch prompt regressions in CI before your users do
Shipwright
Shipwright
Shipwright
Follow
Nov 9
Catch prompt regressions in CI before your users do
#
evals
#
prompts
#
ci
#
claude
Comments
Add Comment
3 min read
Moderation
Can an AI model hide how capable it really is?
deavgprime
deavgprime
deavgprime
Follow
Nov 7
Can an AI model hide how capable it really is?
#
ai
#
evals
#
agents
#
testing
4
 reactions
Comments
Add Comment
10 min read
Moderation
LLM Evals Start as Thirty Test Cases, Not a Platform
Danny Holloran
Danny Holloran
Danny Holloran
Follow
Nov 1
LLM Evals Start as Thirty Test Cases, Not a Platform
#
ai
#
llm
#
evals
#
typescript
Comments
Add Comment
4 min read
Moderation
"đźš« Your Agent Demo Is Not a Release Gate"
Journal A.I.
Journal A.I.
Journal A.I.
Follow
Oct 29
"đźš« Your Agent Demo Is Not a Release Gate"
#
agents
#
evals
#
devops
#
ci
Comments
Add Comment
2 min read
Moderation
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