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
How a model upgrade silently broke our extraction prompt (and how we caught it)
shaun vd
shaun vd
shaun vd
Follow
May 23
How a model upgrade silently broke our extraction prompt (and how we caught it)
#
ai
#
llm
#
devops
#
testing
Comments
Add Comment
3 min read
BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 23
BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090
#
ai
#
llm
#
inference
#
opensource
Comments
Add Comment
3 min read
Context window == RAM?
Mekickdemons
Mekickdemons
Mekickdemons
Follow
May 23
Context window == RAM?
#
discuss
#
agents
#
ai
#
llm
Comments
Add Comment
1 min read
Anna's Archive llms.txt: a routing guide for LLM crawlers
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 23
Anna's Archive llms.txt: a routing guide for LLM crawlers
#
news
#
ai
#
llm
#
dataset
Comments
Add Comment
3 min read
Gemini 3.5 Flash beat 3.1 Pro on coding and agents
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 23
Gemini 3.5 Flash beat 3.1 Pro on coding and agents
#
news
#
ai
#
llm
#
gemini
Comments
Add Comment
3 min read
Google Fills the Sora Gap, Recursive Bets $650M on Self-Improving AI, and the 35-Hour Agent That Changes Everything — May 24, 2026
Mehul Goel
Mehul Goel
Mehul Goel
Follow
May 24
Google Fills the Sora Gap, Recursive Bets $650M on Self-Improving AI, and the 35-Hour Agent That Changes Everything — May 24, 2026
#
ai
#
machinelearning
#
llm
#
datascience
Comments
Add Comment
6 min read
Day 1: I'm Done Writing Prompts by Hand — Meet DSPy
Sumeet Lalla
Sumeet Lalla
Sumeet Lalla
Follow
May 23
Day 1: I'm Done Writing Prompts by Hand — Meet DSPy
#
dspy
#
ai
#
llm
#
python
Comments
Add Comment
4 min read
How a Missing Config Line Cost Me 38x More for the Same Model
Dmitry Platonov
Dmitry Platonov
Dmitry Platonov
Follow
May 22
How a Missing Config Line Cost Me 38x More for the Same Model
#
ai
#
deepseek
#
agents
#
llm
Comments
Add Comment
2 min read
The File Modification Boundary We Found After 12 ForgeFlow Projects
Joseph Yeo
Joseph Yeo
Joseph Yeo
Follow
May 22
The File Modification Boundary We Found After 12 ForgeFlow Projects
#
agents
#
ai
#
llm
#
softwareengineering
Comments
Add Comment
8 min read
We prevented our agents going rogue at runtime.
Kishan GC
Kishan GC
Kishan GC
Follow
May 22
We prevented our agents going rogue at runtime.
#
ai
#
javascript
#
llm
#
backend
Comments
Add Comment
3 min read
An open source LLM eval tool with two independent quality signals
Frank Brsrk
Frank Brsrk
Frank Brsrk
Follow
May 22
An open source LLM eval tool with two independent quality signals
#
showdev
#
ai
#
llm
#
opensource
Comments
Add Comment
4 min read
Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 22
Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench
#
ai
#
llm
#
opensource
#
agents
Comments
Add Comment
4 min read
O fim do “modelo que faz tudo”? Conheça o Conductor, a IA que orquestra outras IAs
Marcos Filipe
Marcos Filipe
Marcos Filipe
Follow
May 22
O fim do “modelo que faz tudo”? Conheça o Conductor, a IA que orquestra outras IAs
#
ai
#
llm
#
agents
#
machinelearning
Comments
Add Comment
8 min read
Google just commoditized the agent stack with a single API call
albe_sf
albe_sf
albe_sf
Follow
May 22
Google just commoditized the agent stack with a single API call
#
ai
#
llm
#
agents
#
devtools
Comments
Add Comment
3 min read
How I use an LLM as a translation judge
Yahya Saleh
Yahya Saleh
Yahya Saleh
Follow
May 22
How I use an LLM as a translation judge
#
llm
#
ai
#
opensource
Comments
Add Comment
1 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