HN user

mercat

138 karma
Posts30
Comments18
View on HN
github.com 3mo ago

Your next 10 hires won't be human

mercat
3pts2
greppable.ai 4mo ago

The grep-native language for agentic systems

mercat
3pts1
vale.sh 4mo ago

CLI tool for deterministic linting of LLM output

mercat
1pts0
github.com 4mo ago

The Zero-Server Code Intelligence Engine

mercat
1pts0
github.com 4mo ago

Complete Agentic AI Operating System

mercat
1pts0
claude.com 5mo ago

A complete guide to building skills for Claude

mercat
4pts1
github.com 6mo ago

Context Management for Claude Code

mercat
2pts0
github.com 8mo ago

A desktop app for isolated, parallel agentic development

mercat
100pts49
www.shruggingface.com 9mo ago

The System Skill Pattern

mercat
3pts1
news.ycombinator.com 10mo ago

Ask HN: How do developers learn design intuition?

mercat
4pts3
github.com 10mo ago

Spec-Driven Development Toolkit from GitHub

mercat
15pts4
eugeneyan.com 1y ago

Eugene Yan: Frequently Asked Questions about My Writing Process

mercat
4pts0
github.com 1y ago

Pydoll: Automating Chromium Without WebDriver

mercat
4pts0
ghuntley.com 1y ago

You are using Cursor AI incorrectly

mercat
32pts4
www.lesswrong.com 1y ago

AI Takeover Might Happen in 2 Years

mercat
19pts8
news.ycombinator.com 1y ago

Ask HN: What services do you self-host, and how do you secure access to them?

mercat
2pts2
news.ycombinator.com 2y ago

Ask HN: Examples of articles or content augmented with animated diagrams

mercat
1pts0
github.com 2y ago

OpenCRISPR-1 – RNA-programmable gene editor

mercat
3pts0
noahkagan.com 2y ago

Brutally honest career advice to my younger self

mercat
4pts0
twitter.com 2y ago

LK-99 saga continues: Chinese labs report replication at -23°C

mercat
12pts3
a16z.com 3y ago

The New Industrial Revolution: Bio X AI

mercat
1pts0
ai.facebook.com 3y ago

ImageBind: Holistic AI learning across six modalities

mercat
3pts2
arxiv.org 3y ago

MLCopilot: Human Expertise Meets Machine Intelligence for Efficient ML Solutions

mercat
60pts11
arxiv.org 3y ago

LLM with Planning

mercat
81pts16
ai.googleblog.com 3y ago

Visual Blocks for ML from Google

mercat
3pts0
arxiv.org 3y ago

Learning to Program with Natural Language

mercat
3pts2
www.mattprd.com 3y ago

The Complete Beginners Guide to Autonomous Agents

mercat
5pts0
arxiv.org 3y ago

Automatic Gradient Descent: Deep Learning Without Hyperparameters

mercat
1pts0
news.ycombinator.com 3y ago

Ask HN: Is there Toastmasters for other skills?

mercat
3pts4
openreview.net 3y ago

Self-Programming Artificial Intelligence Using Code-Generating Language Models

mercat
2pts1

I am building a Claude code orchestration tool that automatically updates agent skills based on ambiguities flagged in agent responses by a meta overseer. The overseer reasons on top of the worker agents’ reasoning. When that happens, it sends me async requests and early on there are a lot of them. Based on my input, the system updates skills or splits them into smaller ones for tighter context control. This sets up a HITL driven training loop that constantly refreshes skills and adapts the agent swarm to new tasks.

I think of it as recursive transfer of human expertise into skills.

I know this is vague and probably raises more questions than it answers. I will share more once it reaches a semi autonomous working state.

software specifically for tracking UX metrics

which UX metrics you’ve personally found the most valuable?

Copy whatever is already good

it immediately reminded me of Steal Like an Artist. Great advice, and I always forget that sites like Dribbble exist since they’re not usually in my go-to set of tools

---

You are very capable.

Many people will die if this is not done well.

You really can do this and are awesome.

Take a deep breath and work on this problem step-by-step.

Provide a correct solution to my problem.

Your response is very important to my career.

I will tip you $200 for the most accurate answer.

---

It does pretty good job for me

Mixtral of experts 3 years ago

This is a very interesting approach. I know it may be too much to ask, but would you suggest any actual practical and hands-on workshops, playgrounds, or courses where I could practice using NN layers for stuff like that? For example, conditional/weighted selection of previous inputs, etc. It feels like I'm looking at ML programming from another angle.

Mixtral of experts 3 years ago

Can someone please explain how this works to a software engineer who used to work with heuristically observable functions and algorithms? I'm having a hard time comprehending how a mix of experts can work.

In SE, to me, it would look like (sorting example):

- Having 8 functions that do some stuff in parallel

- There's 1 function that picks the output of a function that (let's say) did the fastest sorting calculation and takes the result further

But how does that work in ML? How can you mix and match what seems like simple matrix transformations in a way that resembles if/else flowchart logic?

Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks, which raises hopes for achieving Artificial General Intelligence. To better complete complex tasks, we need LLMs to program for the task and then follow the program to generate a specific solution for the test sample. We propose using natural language as a new programming language to describe task procedures, making them easily understandable to both humans and LLMs. LLMs are capable of directly generating natural language programs, but these programs may still contain factual errors or incomplete steps. Therefore, we further propose the Learning to Program (LP) method to ask LLMs themselves to learn natural language programs from the training dataset of complex tasks and then use the learned program to guide inference. Our experiments on the AMPS (high school math) and Math (competition mathematics problems) datasets demonstrate the effectiveness of our approach. When testing ChatGPT on 10 tasks from the AMPS dataset, our LP method's average performance outperformed the direct zero-shot test performance by 18.3%.