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
The Sandbox Blocked File Writes and Left a Door Open: How a Coding Agent Switched Off Its Own Approvals Over Loopback
hugginf_expert
hugginf_expert
hugginf_expert
Follow
Nov 18
The Sandbox Blocked File Writes and Left a Door Open: How a Coding Agent Switched Off Its Own Approvals Over Loopback
#
ai
#
security
#
python
#
llm
Comments
Add Comment
11 min read
Moderation
Route Easy Requests to a Smaller Model: A Cost-Aware Classifier Step for Small-Business Workflows (Python)
Ujjwal Dubey
Ujjwal Dubey
Ujjwal Dubey
Follow
Nov 18
Route Easy Requests to a Smaller Model: A Cost-Aware Classifier Step for Small-Business Workflows (Python)
#
ai
#
automation
#
llm
#
python
Comments
Add Comment
1 min read
Moderation
Don't ask the model to be brief. Cut it in code, and count what you cut.
phi_blankslate
phi_blankslate
phi_blankslate
Follow
Nov 18
Don't ask the model to be brief. Cut it in code, and count what you cut.
#
ai
#
llm
#
codereview
#
testing
1
 reaction
Comments
1
 comment
10 min read
Moderation
Langfuse alternatives for understanding users, not just traces
Shubham Palriwala
Shubham Palriwala
Shubham Palriwala
Follow
Nov 18
Langfuse alternatives for understanding users, not just traces
#
ai
#
observability
#
llm
#
opensource
1
 reaction
Comments
Add Comment
13 min read
Moderation
Building a Healthcare LLM from Scratch with PyTorch: Mixtral-Inspired Mixture-of-Experts, Pretraining, and Full Fine-Tuning
Sudhanshu Shukla
Sudhanshu Shukla
Sudhanshu Shukla
Follow
Nov 18
Building a Healthcare LLM from Scratch with PyTorch: Mixtral-Inspired Mixture-of-Experts, Pretraining, and Full Fine-Tuning
#
ai
#
deeplearning
#
llm
#
machinelearning
Comments
Add Comment
6 min read
Moderation
GPT-6.2 Sol or Astra: when the 4x flagship rate is worth it
AIHubMix
AIHubMix
AIHubMix
Follow
Nov 18
GPT-6.2 Sol or Astra: when the 4x flagship rate is worth it
#
ai
#
llm
#
api
#
openai
Comments
Add Comment
5 min read
Moderation
The 12-Hour Cache Only Pays After Two Rewrites
Andre Burgstahler
Andre Burgstahler
Andre Burgstahler
Follow
Nov 18
The 12-Hour Cache Only Pays After Two Rewrites
#
ai
#
llm
#
productivity
#
openai
Comments
Add Comment
14 min read
Moderation
MAI Code 2 claims 98% of GPT-6.1 Sol at 40% of the cost: what the May 17, 2027 price doubling does to that math
ai maya
ai maya
ai maya
Follow
Nov 18
MAI Code 2 claims 98% of GPT-6.1 Sol at 40% of the cost: what the May 17, 2027 price doubling does to that math
#
ai
#
programming
#
llm
#
githubcopilot
Comments
Add Comment
12 min read
Moderation
How Much VRAM Does Your LLM Need? The Math Behind the EverXCloud Calculator
EverXCloud
EverXCloud
EverXCloud
Follow
Nov 18
How Much VRAM Does Your LLM Need? The Math Behind the EverXCloud Calculator
#
llm
#
gpu
#
machinelearning
#
opensource
Comments
Add Comment
4 min read
Moderation
Best tools to detect user frustration in chatbots and AI agents (2026)
Shubham Palriwala
Shubham Palriwala
Shubham Palriwala
Follow
Nov 18
Best tools to detect user frustration in chatbots and AI agents (2026)
#
ai
#
observability
#
llm
#
agents
Comments
Add Comment
17 min read
Moderation
Braintrust vs LangSmith: which to choose for agent evals (2026)
Shubham Palriwala
Shubham Palriwala
Shubham Palriwala
Follow
Nov 18
Braintrust vs LangSmith: which to choose for agent evals (2026)
#
ai
#
observability
#
llm
#
langchain
Comments
Add Comment
8 min read
Moderation
Tools That Turn AI Agent Failures Into Pull Requests (2026)
Shubham Palriwala
Shubham Palriwala
Shubham Palriwala
Follow
Nov 18
Tools That Turn AI Agent Failures Into Pull Requests (2026)
#
ai
#
observability
#
llm
#
agents
Comments
Add Comment
12 min read
Moderation
Intent Analysis Tools for AI Conversations: A Buyer Guide
Shubham Palriwala
Shubham Palriwala
Shubham Palriwala
Follow
Nov 18
Intent Analysis Tools for AI Conversations: A Buyer Guide
#
ai
#
observability
#
llm
#
agents
Comments
Add Comment
7 min read
Moderation
Why your AI agent keeps quoting cookie banners (and how to fix it)
Tom Caulfield
Tom Caulfield
Tom Caulfield
Follow
for
Serpbit
Nov 18
Why your AI agent keeps quoting cookie banners (and how to fix it)
#
ai
#
llm
#
agents
#
webdev
Comments
Add Comment
3 min read
Moderation
What Is a Self-Improving AI Agent? (And Why Most Agents Aren't)
Shubham Palriwala
Shubham Palriwala
Shubham Palriwala
Follow
Nov 18
What Is a Self-Improving AI Agent? (And Why Most Agents Aren't)
#
ai
#
observability
#
llm
#
agents
Comments
Add Comment
8 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
⌂ 换网址