yiskw (@hereticreader) header
yiskw (@hereticreader) profile picture

yiskw

@hereticreader

Machine Learning / MLOps / Data Engineering / Data Governance / Self Driving Car Engineering / Privacy Engineering

goo.gl/oLrfCA
Joined July 2009
  • Tweets12K
  • Following1.7K
  • Followers170
294Media
Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)Photo by yiskw (@hereticreader)
medium.com/intellyticssoluti…
Do Your AI Agents Actually Need an Ontology Layer, or Just a Better Schema?

Do Your AI Agents Actually Need an Ontology Layer, or Just a Better Schema?

Every engineer building production-grade AI agents eventually hits the same wall. Your agent works brilliantly on simple, isolated prompts…

medium.com
45
huggingface.co/datasets/Cohe…
CohereLabs/10-2026-qwen-investigation-traces · Datasets at Hugging Face

CohereLabs/10-2026-qwen-investigation-traces · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
26
borretti.me/article/no-man-i…
No Man Is an Island

No Man Is an Island

AI makes intellectual contribution superfluous.

borretti.me
14
concurrent.cd/notes/hello-co…
Hello, concurrent.cd - where we research agents and humans working together

Hello, concurrent.cd - where we research agents and humans working together

Every website has its origin story; this is concurrent.cd's, from early conversations about overlapping agents to a first public preview.

concurrent.cd
28
socket.dev/blog/emudhra-brot…
eMudhra, Brotli, and the Long Tail of a Security Fix

eMudhra, Brotli, and the Long Tail of a Security Fix

Fixes for eMudhra and Brotli are out. Getting them everywhere they’re needed means tracking down bundled libraries, runtimes, and certificate stores.

socket.dev
50
grokbotshelf.com/
Grok Bot Shelf

Grok Bot Shelf

Grok Bot templates you can import in one tap.

grokbotshelf.com
18
plannotator.ai/inbox/
Plannotator Inbox

Plannotator Inbox

An async surface for long-running coding agents. Questions and blockers and reviews from every agent arrive in one inbox while they work. Answer and annotate there with Plannotator.

plannotator.ai
20
hey @bot i want that mail.grokbot.com email address
1
17
github.com/TencentCloud/Octo…
GitHub - TencentCloud/Octop: A smarter, self-hosted AI assistant — multi-user, multi-agent.

GitHub - TencentCloud/Octop: A smarter, self-hosted AI assistant — multi-user, multi-agent.

A smarter, self-hosted AI assistant — multi-user, multi-agent. - TencentCloud/Octop

github.com
1
43
topquadrant.com/blog/ontolog…
The Ontology Market: A Guide to Five Very Different Things | TopQuadrant

The Ontology Market: A Guide to Five Very Different Things | TopQuadrant

A market guide to the five artifacts called ontologies: metrics layers, catalog glossaries, learned context graphs, object-action models, and ontologies of record.

topquadrant.com
25
tensorfold.dev/
TensorFold | Run LLMs, Fast.

TensorFold | Run LLMs, Fast.

Run LLMs fast on the GPUs you own with native Metal and CUDA inference.

tensorfold.dev
24
oreilly.com/radar/coding-age…
Coding Agents Love Decision Records

Coding Agents Love Decision Records

The following article originally appeared on Duncan Davidson’s blog and is being republished here with the author’s permission.Decision records give

oreilly.com
21
fx.sh/
fx - Tiny, open, native coding agent

fx - Tiny, open, native coding agent

Tiny, open, native coding agent. A minimal CLI written in Zig, optimized for research and embeddability as part of larger systems.

fx.sh
23
textql.com/blog/ontology-ga
TextQL's Ontology is Now Generally Available | TextQL

TextQL's Ontology is Now Generally Available | TextQL

A file-system approach to consolidating business knowledge as code and giving agents a more direct path from questions to execution.

textql.com
1
34
arxiv.org/abs/2602.14689
Exposing the Systematic Vulnerability of Open-Weight Models to...

Exposing the Systematic Vulnerability of Open-Weight Models to...

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must...

arxiv.org
21
strandsagents.com/blog/intro…
Introducing Strands Decider 2B: a small, open source, decision model

Introducing Strands Decider 2B: a small, open source, decision model

Strands Decider 2B is a small, open source, decision model optimized for fast experimentation, local development, and innovation.

strandsagents.com
28
huggingface.co/Cloudflare/cl…
Cloudflare/clef · Hugging Face

Cloudflare/clef · Hugging Face

Image-Text-to-Text model with 27B parameters. Download, explore files and run it on Hugging Face.

huggingface.co
22
aihero.dev/skills-codebase-d…
The /codebase-design Skill

The /codebase-design Skill

The vocabulary for designing deep modules.

aihero.dev
22
arxiv.org/abs/2609.37725
Context Language Models

Context Language Models

We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted...

arxiv.org
14
chatgpt.com/maps
15
Load more