Menu

#Agents

2138 posts

3 points
Feed·
20 of 2138 posts
I burned all my tokens researching how to save tokens
🖼️
182

I burned all my tokens researching how to save tokens

Hacker News·2 months ago
#g8eqdbi5
#quesma#research#claude#model#agents#tools

How I burned a full Claude limit in 30 minutes and built my own deep research pipeline instead: 3 subscriptions, shared memory, a clear role for each model. You can build the same from what you already pay for.

15s
Read More
How to Choose the Right AI Model for Your Agent (2026 Decision Guide)
🖼️
1

How to Choose the Right AI Model for Your Agent (2026 Decision Guide)

DEV Community·Joaki·5 months ago
#qwxbrQ0z
#ai#agents#productivity#pick#gemini#model

Five years ago picking an AI model was a one-line decision. In 2026 there are six tied flagships, a dozen capable mid-tier models, and the wrong pick will either bankrupt you on tokens or cripple your

15s
Read More
"The CEO Wrote This with MCP" — How I Used an AI Agent to Examine the Translation Industry's Pain Points
🖼️
1

"The CEO Wrote This with MCP" — How I Used an AI Agent to Examine the Translation Industry's Pain Points

DEV Community·Kozo-KI·5 months ago
#ZEjElvVl
#verification#agents#ai#mcp#claude#items

From Dev Community: "The CEO Wrote This with MCP" — How I Used an AI Agent to Examine the Translation Industry's Pain Points

15s
Read More
📰
0

The box an agent runs in — Rohan Adwankar

rohanadwankar.github.io·12 days ago
#BIUFUjRK
#firecracker#microvm#agents#vm#article#ama

One awesome product evolution is that agents (Claude Code, Instinct, Poke, etc) are moving off our local computers so that we can use them on our phones.…

15s
Read More
Which tools do Claude Code, Codex and Cursor choose? We measured 16,893 sessions to find out.
📰
0

Which tools do Claude Code, Codex and Cursor choose? We measured 16,893 sessions to find out.

Hacker News·16 days ago
#zVN5OTkQ
#armature#agents#coding#different#agent#code

We watched almost 17k sessions across different types of personas, with 1,163 prompt variations, 75 repositories and 3 coding agents (Claude Code, Codex, Cursor) actually implementing the solutions instead of just recommending one.

15s
Read More
The Red Queen hypothesis - a new way forward for self-improving AI
🖼️
104

The Red Queen hypothesis - a new way forward for self-improving AI

Hacker News·about 1 month ago
#9I8Ks8c2
#cst#agent#improving#agents#self#queen

At a time when there's widespread interest in self-improving AI, researchers here have tackled one of the central challenges affecting its development by using an approach adapted from evolutionary biology.

15s
Read More
Understanding is the new bottleneck
🖼️
408

Understanding is the new bottleneck

Hacker News·about 1 month ago
#61ovomtd

Agents can write code faster than we can absorb it. Here's why it still matters for humans to understand what they build — and some techniques for doing that efficiently: explainer docs, quizzes, micro-worlds, and shared spaces.

15s
Read More
OJCP — Open Job Context Protocol
🖼️
32

OJCP — Open Job Context Protocol

Hacker News·about 1 month ago
#eBe39vYD
#ojcp#apply#agents#tools#standard#photo

The open standard for agent-consumable job feeds. Discover, reason over, and act on job opportunities with AI agents.

15s
Read More
Humanising LLM Outputs is Dumb
🖼️
228

Humanising LLM Outputs is Dumb

Hacker News·about 1 month ago
#DPr6edxt
#kuber#agents#human#agent#state#tell

The largest tell for me to tell where culture and sentiment is shifting for AI tools is usually X, viral GitHub repositories and Hacker News.…

15s
Read More
Now we have a timeline of the OpenAI accidental attack against Hugging Face
📰
433

Now we have a timeline of the OpenAI accidental attack against Hugging Face

Hacker News·about 1 month ago
#Qy4Ewhfk

OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about “the Hugging Face Incident” (previously on this blog). The video was published yesterday. It’s short and information …

15s
Read More
Introducing Kitesurf: The agent-first browser that runs in V8 isolates on Cloudflare Workers
🖼️
220

Introducing Kitesurf: The agent-first browser that runs in V8 isolates on Cloudflare Workers

Hacker News·about 1 month ago
#cl7zzu2s

We should be giving all agents tools that excel at what’s important for an AI model. Kitesurf is Cloudflare’s new stateless, highly scalable, and cost-effective web browser that runs entirely on top of Workers and was designed specifically for the Agentic…

15s
Read More
Prime Agent: A self-improving RLM agent
🖼️
253

Prime Agent: A self-improving RLM agent

Hacker News·about 1 month ago
#cpa3Yh5r

Prime Agent is our open-source, self-improving coding harness built around two abstractions: the Recursive Language Model (RLM) and the Continual Harness. With Opus 5, it achieves 95.5% on ARC-AGI-3, surpassing the reported human expert baseline.

15s
Read More
US prosecutors charge Atlanta man after GrapheneOS phone wipes itself during airport search
🖼️
0

US prosecutors charge Atlanta man after GrapheneOS phone wipes itself during airport search

Hacker News·about 2 months ago
#2MshPscG

The case centers on Tunick's use of GrapheneOS, an open-source operating system that works on Google Pixel phones and lets users enter a passcode to wipe a...

15s
Read More
Agent swarms and the new model economics
🖼️
0

Agent swarms and the new model economics

Hacker News·2 months ago
#1bUmMH3Q
#cursor#swarm#agents#work#agent#model

We compared old and new agent swarms building SQLite from scratch and found that better coordination delivers similar quality at a fraction of the cost.

15s
Read More