Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
Forem
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Tokenizer Quirks: Claude, GPT, and Gemini Don't Count the Same Text the Same Way
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 29
Tokenizer Quirks: Claude, GPT, and Gemini Don't Count the Same Text the Same Way
#
ai
#
llm
#
python
#
tokenization
Comments
Add Comment
6 min read
Cosine Similarity Lies. Here's What to Use When Your Embeddings All Cluster at 0.85
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 29
Cosine Similarity Lies. Here's What to Use When Your Embeddings All Cluster at 0.85
#
ai
#
rag
#
embeddings
#
llm
Comments
Add Comment
7 min read
The Hidden Tax of Structured Output: How Much Extra You Pay for JSON Mode
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 29
The Hidden Tax of Structured Output: How Much Extra You Pay for JSON Mode
#
llm
#
openai
#
anthropic
#
python
Comments
Add Comment
7 min read
When 'Take a Deep Breath' Stopped Working: Prompt Tricks With an Expiry Date
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 29
When 'Take a Deep Breath' Stopped Working: Prompt Tricks With an Expiry Date
#
ai
#
llm
#
promptengineering
#
machinelearning
Comments
Add Comment
7 min read
Build vs. Buy vs. Prompt Is the Wrong AI Question
Keith Azodeh
Keith Azodeh
Keith Azodeh
Follow
Apr 29
Build vs. Buy vs. Prompt Is the Wrong AI Question
#
ai
#
architecture
#
llm
#
product
Comments
Add Comment
8 min read
Alibaba's Qwen3.6-Max-Preview Challenges GPT-5.4 on Agentic Coding
Marcus Rowe
Marcus Rowe
Marcus Rowe
Follow
Apr 29
Alibaba's Qwen3.6-Max-Preview Challenges GPT-5.4 on Agentic Coding
#
qwen
#
alibaba
#
agenticcoding
#
llm
Comments
Add Comment
7 min read
Cut Claude Code Token Usage by Delegating to Cheaper Models with Boss Mode
Thomas Lau
Thomas Lau
Thomas Lau
Follow
Apr 29
Cut Claude Code Token Usage by Delegating to Cheaper Models with Boss Mode
#
claude
#
llm
#
productivity
#
devtools
Comments
Add Comment
4 min read
Why ChatGPT will silently lie about your bank statement (and how to catch it)
Kyr
Kyr
Kyr
Follow
Apr 29
Why ChatGPT will silently lie about your bank statement (and how to catch it)
#
ai
#
llm
#
python
#
datascience
Comments
Add Comment
4 min read
MCP in Production Reality vs the Spec
claire nguyen
claire nguyen
claire nguyen
Follow
Apr 29
MCP in Production Reality vs the Spec
#
devops
#
infrastructure
#
llm
#
sre
Comments
Add Comment
3 min read
Who Owns the Code Claude Wrote? The Legal Mess No One's Talking About
Andrew Kew
Andrew Kew
Andrew Kew
Follow
Apr 29
Who Owns the Code Claude Wrote? The Legal Mess No One's Talking About
#
discuss
#
ai
#
llm
#
programming
Comments
Add Comment
3 min read
Building a Multi-Agent Travel Planner: From a One-Sentence Prompt to a Validated, Budget-Aware Itinerary
Palash1417
Palash1417
Palash1417
Follow
May 3
Building a Multi-Agent Travel Planner: From a One-Sentence Prompt to a Validated, Budget-Aware Itinerary
#
ai
#
python
#
llm
#
opensource
1
 reaction
Comments
Add Comment
8 min read
How Much VRAM Do You *Actually* Need for Local LLMs?
Thurmon Demich
Thurmon Demich
Thurmon Demich
Follow
Apr 29
How Much VRAM Do You *Actually* Need for Local LLMs?
#
ai
#
llm
#
machinelearning
#
performance
Comments
Add Comment
2 min read
Building Reliable AI Systems: Why Prompting Isn’t Enough
Pavan Kumar Appannagari
Pavan Kumar Appannagari
Pavan Kumar Appannagari
Follow
Apr 29
Building Reliable AI Systems: Why Prompting Isn’t Enough
#
generativeai
#
llm
#
systemdesign
#
architecture
Comments
Add Comment
3 min read
GPT-5.5: OpenAI’s Smartest Model Yet — But Is the Hype Bigger Than the Model?
Akshat Uniyal
Akshat Uniyal
Akshat Uniyal
Follow
Apr 29
GPT-5.5: OpenAI’s Smartest Model Yet — But Is the Hype Bigger Than the Model?
#
chatgpt
#
openai
#
ai
#
llm
Comments
Add Comment
5 min read
AI Testing Is Not Magic — You Already Know How to Do It
Liudas
Liudas
Liudas
Follow
Apr 29
AI Testing Is Not Magic — You Already Know How to Do It
#
ai
#
llm
#
machinelearning
#
testing
2
 reactions
Comments
Add Comment
4 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a blogging-forward open source social network where we learn from one another
Log in
Create account