DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?

Harnesses drive massive score jumps
p0rt profile

The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?

#ai #llm #agents #machinelearning
22
Comments 44
10 min read
AI Weekly: GPT-5.6-Cyber, Muse Glimmer, and the Agent Browser
alexmercedcoder profile

AI Weekly: GPT-5.6-Cyber, Muse Glimmer, and the Agent Browser

#ai #llm #openai #security
1
Comments 1
24 min read
Challenging Tokenization: An LLM Architecture Experiment Without a Tokenizer
emyltonleunufna profile

Challenging Tokenization: An LLM Architecture Experiment Without a Tokenizer

#nlp #llm #ai #engineering
Comments
3 min read
Probe vs Prose: what the verifier-sharing-your-text-channel really costs
zxpmail profile

Probe vs Prose: what the verifier-sharing-your-text-channel really costs

#ai #llm #agents #testing
4
Comments 2
16 min read
AI This Week (Aug 2026): Qwen3.8 Max, DeepSeek V4-Flash, and Models Shipping Like Patches
ai_maya_063fc568e157562fd profile

AI This Week (Aug 2026): Qwen3.8 Max, DeepSeek V4-Flash, and Models Shipping Like Patches

#news #ai #machinelearning #llm
Comments
2 min read
300+ languages doesn't mean what you think: three tiers of code understanding
nhirschfeld profile

300+ languages doesn't mean what you think: three tiers of code understanding

#ai #llm #programming #software
Comments
7 min read
Keeping the LLM out of the verdict
quemtrouxe profile

Keeping the LLM out of the verdict

#ai #architecture #llm #python
Comments 1
5 min read
How parallel AI agents should talk to each other (and the bug that proved it)
ahmadammar profile

How parallel AI agents should talk to each other (and the bug that proved it)

#ai #agents #llm #architecture
1
Comments 2
3 min read
I tried to patch a blind spot in my own MCP tool. The patch and a false-positive bug cancel out.
churik5 profile

I tried to patch a blind spot in my own MCP tool. The patch and a false-positive bug cancel out.

#security #ai #llm #mcp
2
Comments
5 min read
I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path
mandarvshinde profile

I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path

#showdev #python #ai #llm
Comments
2 min read
I created a tool to inspect full python codebases
ssmm1983 profile

I created a tool to inspect full python codebases

#llm #python #ai #code
Comments
1 min read
When your benchmark is wrong and your model is right
hammertoe profile

When your benchmark is wrong and your model is right

#ai #llm #machinelearning
1
Comments
7 min read
What changed in Apiarium after developers started using it
manolito99 profile
Lolo

What changed in Apiarium after developers started using it

#ai #api #llm #software
19
Comments 3
3 min read
"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"
ai_maya_063fc568e157562fd profile

"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"

#ai #llm #machinelearning #opensource
Comments
7 min read
🤖 AI Context Engineering (Part 4): AI Agents - From Tool Calling to Multi-Step Workflows
fazal_mansuri_ profile

🤖 AI Context Engineering (Part 4): AI Agents - From Tool Calling to Multi-Step Workflows

#ai #llm #agents #softwareengineering
1
Comments
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.