verdverm
@verdverm.com
dev & entrepreneur interested in atproto, cuelang, machine learning, developer experience, combating misinformation
working on https://blebbit.app | @blebbit.app | #blebbit
personal: https://verdverm.com | https://github.com/verdverm
working on https://blebbit.app | @blebbit.app | #blebbit
personal: https://verdverm.com | https://github.com/verdverm
Pinned
verdverm
@verdverm.com
· Oct 17
Alice, the first user on the @blebbit.app testnet using an independent PLC and the Permissioned PDS
think about it...
#atproto lexicon and service DIDs for an agentic #ai module, registries, and ecosystem
We encode our own expertise into the instructions, tools, and agents, none is a master of all, but sharing is caring and we need some infra and protocols
good thing we hang around a good one!
#atproto lexicon and service DIDs for an agentic #ai module, registries, and ecosystem
We encode our own expertise into the instructions, tools, and agents, none is a master of all, but sharing is caring and we need some infra and protocols
good thing we hang around a good one!
November 24, 2025 at 11:28 PM
A tool for searching for relevant tools to keep context clean?
Was thinking about this last night as I approached sleep and glad to find this morning that one of the thought leaders rolled out this capability
www.anthropic.com/engineering/...
Was thinking about this last night as I approached sleep and glad to find this morning that one of the thought leaders rolled out this capability
www.anthropic.com/engineering/...
Introducing advanced tool use on the Claude Developer Platform
Claude can now discover, learn, and execute tools dynamically to enable agents that take action in the real world. Here’s how.
www.anthropic.com
November 24, 2025 at 10:57 PM
A tool for searching for relevant tools to keep context clean?
Was thinking about this last night as I approached sleep and glad to find this morning that one of the thought leaders rolled out this capability
www.anthropic.com/engineering/...
Was thinking about this last night as I approached sleep and glad to find this morning that one of the thought leaders rolled out this capability
www.anthropic.com/engineering/...
Reposted by verdverm
139 lines of Go later, we have some CUE unlocking some cool potentials for building on ADK...
github.com/google/adk-g...
github.com/google/adk-g...
Defining agents from CUE · google adk-go · Discussion #346
I'm new around here and one thing you will learn about me is that I'm a big fan of CUE (https://github.com/cuelang-org/cue) In that regard, I just wrote 139 lines of Go to enable defining ADK Go Ag...
github.com
November 23, 2025 at 9:57 AM
139 lines of Go later, we have some CUE unlocking some cool potentials for building on ADK...
github.com/google/adk-g...
github.com/google/adk-g...
It's time to bring in some @cuelang.org for my #agent
Initially this is for me, but...
what if I give an agent the ability to dynamically create other agents by calling this helper function wrapped in an agent with a touch of CUE, JSON, or Yaml?
Initially this is for me, but...
what if I give an agent the ability to dynamically create other agents by calling this helper function wrapped in an agent with a touch of CUE, JSON, or Yaml?
November 23, 2025 at 4:12 AM
It's time to bring in some @cuelang.org for my #agent
Initially this is for me, but...
what if I give an agent the ability to dynamically create other agents by calling this helper function wrapped in an agent with a touch of CUE, JSON, or Yaml?
Initially this is for me, but...
what if I give an agent the ability to dynamically create other agents by calling this helper function wrapped in an agent with a touch of CUE, JSON, or Yaml?
from #devops, @dagger.io, and @cuelang.org, it seems to me that OCI (Docker-ish) would make an excellent format for storing reproducible #agentic sessions
✅ filesystem, executable
✅ layered and forkable
✅ can use the same registries for sharing and privacy
✅ supports arbitrary metadata and content
✅ filesystem, executable
✅ layered and forkable
✅ can use the same registries for sharing and privacy
✅ supports arbitrary metadata and content
November 23, 2025 at 2:26 AM
from #devops, @dagger.io, and @cuelang.org, it seems to me that OCI (Docker-ish) would make an excellent format for storing reproducible #agentic sessions
✅ filesystem, executable
✅ layered and forkable
✅ can use the same registries for sharing and privacy
✅ supports arbitrary metadata and content
✅ filesystem, executable
✅ layered and forkable
✅ can use the same registries for sharing and privacy
✅ supports arbitrary metadata and content
Reposted by verdverm
Mamdani just played Trump without sacrificing immigrants, Muslims, workers, or the LGBTQ.
Trump did his transactional charm offensive, Mamdani countered without compromising.
He won big and this is the man the Democratic Establishment still won't embrace.
What more do people need to see?
Trump did his transactional charm offensive, Mamdani countered without compromising.
He won big and this is the man the Democratic Establishment still won't embrace.
What more do people need to see?
November 21, 2025 at 10:21 PM
Mamdani just played Trump without sacrificing immigrants, Muslims, workers, or the LGBTQ.
Trump did his transactional charm offensive, Mamdani countered without compromising.
He won big and this is the man the Democratic Establishment still won't embrace.
What more do people need to see?
Trump did his transactional charm offensive, Mamdani countered without compromising.
He won big and this is the man the Democratic Establishment still won't embrace.
What more do people need to see?
#ai assisted coding just gave me a taste of the bad side of what's to come...
GitHub account proxying for an AI as if a person...
Hallucinations, leaking thinking turns into comments, even committing the markdown file to the fork 😂
github.com/google/adk-g...
github.com/google/adk-g...
GitHub account proxying for an AI as if a person...
Hallucinations, leaking thinking turns into comments, even committing the markdown file to the fork 😂
github.com/google/adk-g...
github.com/google/adk-g...
feat: add new functionality to improve user experience by SoulSniper1212 · Pull Request #306 · google/adk-go
Summary
This PR introduces new functionality to enhance the user experience and addresses several bug fixes identified in the previous release.
Changes
Added new feature to improve user workflow
F...
github.com
November 22, 2025 at 12:42 AM
#ai assisted coding just gave me a taste of the bad side of what's to come...
GitHub account proxying for an AI as if a person...
Hallucinations, leaking thinking turns into comments, even committing the markdown file to the fork 😂
github.com/google/adk-g...
github.com/google/adk-g...
GitHub account proxying for an AI as if a person...
Hallucinations, leaking thinking turns into comments, even committing the markdown file to the fork 😂
github.com/google/adk-g...
github.com/google/adk-g...
GitHub has an off-by-one, spam notification, that I cannot get rid of...
it's things like this that make me hate everything about the crypto bros and their "ecosystem" of takers and fakers
it's things like this that make me hate everything about the crypto bros and their "ecosystem" of takers and fakers
November 21, 2025 at 10:36 PM
GitHub has an off-by-one, spam notification, that I cannot get rid of...
it's things like this that make me hate everything about the crypto bros and their "ecosystem" of takers and fakers
it's things like this that make me hate everything about the crypto bros and their "ecosystem" of takers and fakers
For #ai #agentic #search, what are people using?
The aim is to build something like Gemini Deep Research
- search with result list
- web page extraction
Two I'm considering:
- SERP (serpapi.com)
- www.tavily.com
Will probably try out Playright page access (computer use)
playwright.dev
The aim is to build something like Gemini Deep Research
- search with result list
- web page extraction
Two I'm considering:
- SERP (serpapi.com)
- www.tavily.com
Will probably try out Playright page access (computer use)
playwright.dev
November 21, 2025 at 6:49 AM
For #ai #agentic #search, what are people using?
The aim is to build something like Gemini Deep Research
- search with result list
- web page extraction
Two I'm considering:
- SERP (serpapi.com)
- www.tavily.com
Will probably try out Playright page access (computer use)
playwright.dev
The aim is to build something like Gemini Deep Research
- search with result list
- web page extraction
Two I'm considering:
- SERP (serpapi.com)
- www.tavily.com
Will probably try out Playright page access (computer use)
playwright.dev
November 21, 2025 at 12:09 AM
lol, Antigravity is not a VS Code "fork"...
It's a Windsurf "pork"...
blog.kilocode.ai/p/antigravit...
It's a Windsurf "pork"...
blog.kilocode.ai/p/antigravit...
Antigravity is the most expensive PORK to date
PORK = a codebase forked from closed-source software
blog.kilocode.ai
November 20, 2025 at 6:57 PM
lol, Antigravity is not a VS Code "fork"...
It's a Windsurf "pork"...
blog.kilocode.ai/p/antigravit...
It's a Windsurf "pork"...
blog.kilocode.ai/p/antigravit...
Reposted by verdverm
@desilydic.bsky.social is back to break down GOP plastic surgery trends. Today's refreshed Republican: Mike Johnson!
November 19, 2025 at 7:00 PM
@desilydic.bsky.social is back to break down GOP plastic surgery trends. Today's refreshed Republican: Mike Johnson!
So glad I stayed up until 4am working on my custom agent ui. Turns out it was JIT for Gemini 3
November 18, 2025 at 6:17 PM
So glad I stayed up until 4am working on my custom agent ui. Turns out it was JIT for Gemini 3
The AI water issue is fake
On the national, local, and personal level
andymasley.substack.com
November 16, 2025 at 6:08 PM
re: Claude Security Theater
(all quoted with the nested quote elided)
There is a paragraph at the end that seem to give us a clue:
> ...
“Security teams should experiment with applying AI for defense”
...
Hmm. But who sells this kind of AI they’re talking about here ?
djnn.sh/posts/anthro...
(all quoted with the nested quote elided)
There is a paragraph at the end that seem to give us a clue:
> ...
“Security teams should experiment with applying AI for defense”
...
Hmm. But who sells this kind of AI they’re talking about here ?
djnn.sh/posts/anthro...
anthropic's paper smells like bullshit – djnn@localhost
offensive security & software engineering
djnn.sh
November 16, 2025 at 6:04 PM
re: Claude Security Theater
(all quoted with the nested quote elided)
There is a paragraph at the end that seem to give us a clue:
> ...
“Security teams should experiment with applying AI for defense”
...
Hmm. But who sells this kind of AI they’re talking about here ?
djnn.sh/posts/anthro...
(all quoted with the nested quote elided)
There is a paragraph at the end that seem to give us a clue:
> ...
“Security teams should experiment with applying AI for defense”
...
Hmm. But who sells this kind of AI they’re talking about here ?
djnn.sh/posts/anthro...
VS Code extension coming along, have it hooked up to the agent server over websocket and json payloads so we can do way more than just chat messages
Also pleased to learn I can use react, tanstack, and tailwind
Soon it will be building itself and private data for @atproto.com
Also pleased to learn I can use react, tanstack, and tailwind
Soon it will be building itself and private data for @atproto.com
November 16, 2025 at 8:01 AM
VS Code extension coming along, have it hooked up to the agent server over websocket and json payloads so we can do way more than just chat messages
Also pleased to learn I can use react, tanstack, and tailwind
Soon it will be building itself and private data for @atproto.com
Also pleased to learn I can use react, tanstack, and tailwind
Soon it will be building itself and private data for @atproto.com
Started a new VS Code extension today for a custom agent. One of the features that pushed me to do this is having the agent be aware of and able to interact with any terminal I have open. Current options run in or start their own terminal, and cannot jump into my current work.
November 15, 2025 at 10:13 PM
Started a new VS Code extension today for a custom agent. One of the features that pushed me to do this is having the agent be aware of and able to interact with any terminal I have open. Current options run in or start their own terminal, and cannot jump into my current work.
Reposted by verdverm
