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
Taming Clinical Hallucinations: How We Mapped Colloquial Patient Slang to 350,000+ SNOMED CT Concepts Using AWS Bedrock & Vector Disambiguation
saif ur rahman
saif ur rahman
saif ur rahman
Follow
Nov 19
Taming Clinical Hallucinations: How We Mapped Colloquial Patient Slang to 350,000+ SNOMED CT Concepts Using AWS Bedrock & Vector Disambiguation
#
ai
#
aws
#
llm
#
machinelearning
Comments
Add Comment
8 min read
Moderation
I put my multi-model dispatch queue and its monthly spend beside the Claude Code chat. 1,330 lines, 37 ms.
Zhuojun Li
Zhuojun Li
Zhuojun Li
Follow
Nov 18
I put my multi-model dispatch queue and its monthly spend beside the Claude Code chat. 1,330 lines, 37 ms.
#
claudecode
#
ai
#
llm
#
opensource
1
reaction
Comments
Add Comment
5 min read
Moderation
Five entry types that belong in your AI agent's memory file
KarmaBox
KarmaBox
KarmaBox
Follow
Nov 19
Five entry types that belong in your AI agent's memory file
#
ai
#
agents
#
llm
#
architecture
Comments
Add Comment
12 min read
Moderation
Public trial: looking for real agent traces that break doneattr — an open-source diagnostic CLI for false “done” claims (not validated yet)
liao-zhizhi
liao-zhizhi
liao-zhizhi
Follow
Nov 19
Public trial: looking for real agent traces that break doneattr — an open-source diagnostic CLI for false “done” claims (not validated yet)
#
ai
#
llm
#
testing
#
opensource
Comments
Add Comment
2 min read
Moderation
AI agent observability in financial services: what evidence do your risk, compliance and audit teams actually ask you to show?
Bonree-Js
Bonree-Js
Bonree-Js
Follow
Nov 19
AI agent observability in financial services: what evidence do your risk, compliance and audit teams actually ask you to show?
#
ai
#
devops
#
llm
#
agents
Comments
Add Comment
5 min read
Moderation
A Correct Outcome Does Not Necessarily Mean the Process Was Acceptable
Kevcam2407
Kevcam2407
Kevcam2407
Follow
Nov 18
A Correct Outcome Does Not Necessarily Mean the Process Was Acceptable
#
testing
#
ai
#
security
#
llm
Comments
Add Comment
5 min read
Moderation
Your use case is not in the benchmarks
Bryan Lee
Bryan Lee
Bryan Lee
Follow
Nov 18
Your use case is not in the benchmarks
#
ai
#
llm
#
machinelearning
#
programming
Comments
Add Comment
11 min read
Moderation
Agent skills after the install button: 6 reads on loading, gain checks, conflicts, state machines and trust
Redreamality
Redreamality
Redreamality
Follow
Nov 19
Agent skills after the install button: 6 reads on loading, gain checks, conflicts, state machines and trust
#
ai
#
llm
#
agents
#
programming
Comments
Add Comment
4 min read
Moderation
Gemini 4 Neon: The Balance Point Between Carbon and Hydrogen — Benchmarks, API Pricing, and Orchestrator Workflows
UULab
UULab
UULab
Follow
Nov 19
Gemini 4 Neon: The Balance Point Between Carbon and Hydrogen — Benchmarks, API Pricing, and Orchestrator Workflows
#
ai
#
gemini
#
llm
#
api
Comments
Add Comment
10 min read
Moderation
Same AI model, five weeks later: the cheapest provider had changed
uehara
uehara
uehara
Follow
Nov 19
Same AI model, five weeks later: the cheapest provider had changed
#
ai
#
llm
#
openrouter
#
deepseek
Comments
Add Comment
7 min read
Moderation
Scale the Model, Scale the Harness: Unlocking a 2 Leap in Mathematical Reasoning
Edwin Jongsma
Edwin Jongsma
Edwin Jongsma
Follow
Nov 19
Scale the Model, Scale the Harness: Unlocking a 2 Leap in Mathematical Reasoning
#
ai
#
machinelearning
#
llm
#
opensource
Comments
Add Comment
2 min read
Moderation
One sentence stopped my AI agents inventing data. Bad data that looked normal still fooled them.
Houssain El marouni
Houssain El marouni
Houssain El marouni
Follow
Nov 18
One sentence stopped my AI agents inventing data. Bad data that looked normal still fooled them.
#
ai
#
testing
#
llm
#
opensource
Comments
Add Comment
5 min read
Moderation
GPT-6.2 Astra vs. Sol: Benchmarks and API Pricing
Magnus
Magnus
Magnus
Follow
for
Modelflare
Nov 19
GPT-6.2 Astra vs. Sol: Benchmarks and API Pricing
#
ai
#
llm
#
openai
#
api
Comments
Add Comment
12 min read
Moderation
Generating YouTube titles and thumbnail ideas from a transcript without putting words in the creator's mouth
Mohamed Mokbel
Mohamed Mokbel
Mohamed Mokbel
Follow
Nov 19
Generating YouTube titles and thumbnail ideas from a transcript without putting words in the creator's mouth
#
showdev
#
ai
#
video
#
llm
Comments
Add Comment
2 min read
Moderation
I Autoscaled My LLM on Queue Depth. It Scaled Down Under Full Load.
Ahmet Ozan GAZİ
Ahmet Ozan GAZİ
Ahmet Ozan GAZİ
Follow
Nov 18
I Autoscaled My LLM on Queue Depth. It Scaled Down Under Full Load.
#
kubernetes
#
llm
#
devops
#
ai
4
reactions
Comments
3
comments
10 min read
Moderation
👋
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