openclaw 'ai personal assistant' that you can interact w through your regular chat apps it says

the skill.md for Moltbook.

'a social network for AI agents' wut?

blogger Fabrizio Ferri Benedetti on their 4 modes of using AI in technical writing. - watercooler conversations, to get code explained - text suggestions while writing/coding (esp for repeating patterns in your work - providing context / constraints / intent to generate first drafts, restructure content, or boilerplate commentary etc. - a robotic assembly line, to do checks, tests and rewrites. MCP/skills involved.

Not either/or but switching between modes

Also used openhands for a test. says it needs intervention (not fully delegated iow)

ah, turtles all the way down. using AI to generate the task specs.

A discrete task description to be treated like a project in the GTD sense (anything above 2 steps is a project). At what point is this overkill, as in templating this project description may well lead to having the solutions once you've done this.

indeed. as mentioned above too. n:: My sense that this is a learning mode akin to the haptic feedback of working on things by hand.

What I mentioned above: to delegate you need to be able to fully describe and provide context for a discrete task.

A list of async coding agents in #2025/08 github, openai, google mentioned. OpenHands is the one open source mentioned. mentions that command line tools can be used (if integrated w e.g. github actions to tie into the coding environment) - [ ] check out openhands agent by All Hands

not just time saving, but a restructuring. So, any description of how the structure changes (before / after style) further down?

do multiple things in parallel. note: The assumption here that the context is coding

compares delegation to formulating a 'ticket'. Assumes well defined tasks up front I think, rather than exploratory things.

async means no handholding, but delegation instead. That is enticing obviously, but assumes unattended execution can be trusted. Seems a big if.

cloud agent = background agent = async agent

Async coding agents is a diff kind of vibe coding: you give it a defined more complex tasks and it will work in the background and come back with an outcome.

https://web.archive.org/web/20260125124811/https://elite-ai-assisted-coding.dev/p/working-with-asynchronous-coding-agents Eleanor Berger, August 2025.

on asynchronous coding agents

"AI Productivity Index for Agents (APEX-Agents)" ref'd in [[Are AI agents ready for the workplace A new benchmark raises doubts TechCrunch]] paper: APEX-Agents in Zotero

Are AI agents ready for the workplace? Asking a question in a headline, means the answer is 'no'.

Cursor is an AI using code editor. It connects only to US based models (OpenAI, Anthropic, Google, xAI), and your pricing tier goes piecemeal to whatever model you're using.

Both an editor, and a CLI environment, and integrations with things like Slack and Github. This seems a building block for US-centered agentic AI silo forming for dev teams.

You can get LLMs to snitch on you. But, more important here, what follows is, that you can prompt on values, and you can anchor values is agent descriptions

async coding agents: prompt and forget

author def of coding agents

recognisable, ai agents as chunked / abstracted away automation. This also creates the pitfall [[After claiming to redeploy 4,000 employees and automating their work with AI agents, Salesforce executives admit We were more confident about…. - The Times of India]] where regular automation is replaced by AI.

Most useful for search and for coding

uses as def for agent 'llm that runs tools in a loop to achieve a goal' (I think he means desired result, not goal)

Combining multiple MCP servers creates a more capable set-up.

prompts are user invoked (hey AgentX, go do..) and may contain next to instructions also references and tools. So a prompt may be a full workflow.

n:: MCP servers typically provide three types of building blocks, a) Tools that an LLM can call, b) resources that are read-only resources to an LLM, c) prompts, prewritten instructions templates, i.e. agent descriptions, that outline specific tools and resources to use. So for agentic stuff you'd have an MCP server providing templates which in turn list tools and resources.

MCP plugin for Obsidian, that works with Claude Code

MCP in Obsidian?

ha, you can distract chatbots, as we've seen from the start. This is the classic 'it's not for me but for my mom' train ticket sales automation hangup in response to 'to which destination would you like a ticket', and then 'unknown railway station 'for my mom' in a new guise. And they didn't even expect that to happen? It's an attack service!

wtf? Why ever use AI to send out a survey, something you probably already had fully automated beforehand. 'deterministic triggers' is a euphemism for regular scripted automation like 'clicking done on a ticket triggers an e-mail for feedback', which we've had for decades.

Whut? AI-so-human! Vgl 8-bits-schuifregister metafoor. [[Korte termijngeheugen 7 dingen 30 secs 20250630104247]] Is there a chunking style work-around? Where does this originate, token limit, bite sizes?

meaning? probabilities isn't random and isn't perfect. Dial down the temp on models and what do you get?

Salesforce upon roll-out of ai-agents dumped half their staff at support. ouch.

Salesforce moving back from fully embracing llms, towards regular automation. I think this is symptomatic in diy enthusiasm too: there is likely an existing 'regular' automation that helps more.

https://web.archive.org/web/20251228094705/https://timesofindia.indiatimes.com/technology/tech-news/after-laying-off-4000-employees-and-automating-with-ai-agents-salesforce-executives-admit-we-were-more-confident-about-/amp_articleshow/126121875.cms

How does this not impact brand reputation and revenue of Salesforce?

this type of thing sounds like what I thought wrt annotation of [[AI agents als virtueel team]]. The example prompts of questions make me think of [[Filosofische stromingen als gereedschap 20030212105451]] die al per stroming een vraagstramien bevat. Making persona's of diff thinking styles, lines of questioning. Idem for reviews, or starting a project etc.

https://web.archive.org/web/20251129105205/https://www.csoonline.com/article/4097087/ai-browsers-can-be-tricked-with-malicious-prompts-hidden-in-url-fragments.html

Named anchors in URLs can be used for prompt injection in AI browser assistants. # URL parts are only evaluated in browser, and not send to servers. AI assistants in browsers do read them though.

• Microsoft Azure showcased modernization of cloud infrastructure at Microsoft Ignite 2025, focusing on reliability, security, and AI-era performance.
• The strategy includes strengthening Azure’s global foundation, modernizing workloads with advanced systems (Azure Cobalt, Azure Boost, AKS Automatic, HorizonDB), and transforming team workflows through AI agents like Azure Copilot and GitHub Copilot.
• Azure Copilot introduces an agentic cloud operations model with specialized agents for migration, deployment, optimization, observability, resiliency, and troubleshooting to automate tasks and enhance innovation.
• Azure’s AI infrastructure supports global scale with over 70 regions and datacenters, featuring Fairwater AI datacenters with liquid cooling, a dedicated AI WAN, and NVIDIA GB300 GPUs to deliver unmatched capacity and speed.
• Innovations like Azure Boost offload virtualization tasks onto specialized hardware, improving disk throughput and network performance; AKS Automatic simplifies Kubernetes management for fast, reliable app deployment.
• Azure HorizonDB for PostgreSQL offers scalable, AI-integrated databases and new partnerships (e.g., SAP Business Data Cloud Connect) facilitate data sharing across platforms.
• Azure emphasizes operational excellence with zone-redundant networking, automated fault detection, and resilience co-engineered with customers via Azure Resiliency.
• Security improvements include Azure Bastion Secure by Default for hardened VM access, Network Security Perimeter for centralized firewall control, and AI-powered defenses like Web Application Firewall with Captcha.
• Modernization supports a mix of legacy and cloud-native systems with AI tools enabling faster migration and modernization for .NET, Java, SQL Server, Oracle, and PostgreSQL workloads.
• Azure enables faster, more efficient modernization and management across infrastructure, improving governance, compliance, and cost-effectiveness.
• The cloud future is agentic, intelligent, and human-centered, with continued innovation in Azure infrastructure, AI agents, and open-source contributions driving business growth.

for - comparison - multi-level agents - scaffolding

for - adjacency - TAG - living systems - cell agents - consciousness agent

https://web.archive.org/web/20250630134724/https://www.theregister.com/2025/06/29/ai_agents_fail_a_lot/

'agent washing' Agentic AI underperforms, getting at most 30% tasks right (Gemini 2.5-Pro) but mostly under 10%.

Article contains examples of what I think we should agentic hallucination, where not finding a solution, it takes steps to alter reality to fit the solution (e.g. renaming a user so it was the right user to send a message to, as the right user could not be found). Meredith Witthaker is mentioned, but from her statement I saw a key element is missing: most of that access will be in clear text, as models can't do encryption. Meaning not just the model, but the fact of access existing is a major vulnerability.

https://web.archive.org/web/20241128202254/https://www.aitidbits.ai/p/open-source-agents?utm_source=post-email-title

On AI Agents, open source tools. Vgl [[small band AI personal assistant]] these tools need to be small and personal. Not platformed, but local.

https://web.archive.org/web/20241115135937/https://workforcefuturist.substack.com/p/ai-agents-building-your-digital-workforce

On AI agents, and the engineering to get one going. A few things stand out at first glance: frames it as the next hype (Vgl plateau in model dev), says it's for personal tools (doesn't square w hype which vc-fuelled, personal tools not of interest to them), and mentions a few personal use cases. e.g. automation, vgl [[Open Geodag 20241107100937]] Ed Parsons of Google AI on the same topic.

Like MS Teams is your teammate, like your accounting software is your teammate. Do they call their own Atlassian tools teammates too? Do these people at Atlassian get out much? Or don't they realise that the other handles in their Slack channel represent people not just other bits of software? Remote work led to dehumanizing co-workers? How else to come up with this wording? Nothing makes you sound more human like talking about 'deploying' teammates. My money is on this article was mostly generated. Reverse-Turing says it's up to them to say otherwise.

And as usual in these articles the truth is at the end, it's again just promises.

At the center of an AI application, like what, mechanical Turks?

After a section celebrating examples doing just that!

This sentence preceded by 2 examples where interactions and collaboration were delegated to bots to hand-out generated warm feelings, does not convey much positive about Atlassian. This basically says that a lot of human interaction in the or is seen as meaningless, and please go do that with a bot, not a colleague. Did their branding ai-agent write this?

Like Linked-In wants you to congratulate people on their work-anniversary?

Welcome in our company, you'll meet your first human colleague after you've interacted with our onboarding-robot for a week. No thanks.

anthropomorphing should be in this article's don't list. 'inviting someone on your team' is a highly social thing. Bringing in a software tool is a different thing.

An AI agent to help you speak corporate better, because no one actually writes/reflects/talks that way themselves. How did the receivers of these reports perceive this change in reports? Did they think it was better Q, or did all reflections now read the same?

Low end tasks for agents don't really need AI do they. Vgl Ed Parsons last week wrt automation as AI focus.

This does not fully chime with my own perception of (AI) agents. At least the titles don't. The tails of descriptions 'trained to adhere to brand guidelines' and 'expertise in internal decision-making framework' makes more sense. I suppose I also rail against this being the org's agents, and don't seem to be the team's / pro's agents. Vibes of having an automated political officer in your unit. -[ ] explore nature and examples of AI agents better for within individual pro scope #ontwikkelingspelen #netag #30mins #4hr

Weird notion of remote work as only screen interaction. My team works remote, meaning they think independent from any screen tasks.

https://web.archive.org/web/20241012060204/https://www.felicis.com/insight/the-agent-economy

for the image listing various AI 'agent' services. Some seem dubious as example, and not agents but generally 'ai tools'. -[ ] maak lijst v voorbeelden uit illustratie [[241012Felicislijstaiagentscorps.png]] #15mins mbt acties/sectoren die interessant lijken. Now an agent for that task....

so much wrong with that phrase and a tell for how these corps view this tech. let's have your customers talk to machines.

seems that way, and to mostly remain that way. I'd be curious to incorporate agents in my tasks ([[Aazai CL]] list of such tasks)

also burying the lede much, this is the key verdict and it's in the penultimate paragraph?

Real agents would start at the individual level. It all smacks so much of corps automating away their own direct interaction with customers, bc they're a pain to talk to. Blind, see gripes of existing silo customers about the impossibility getting to talk to someone

almost by def asymmetric, leaving customers to talk to a blind wall.

The gap is a constant I suspect. In the tech itself, since my EE days, and in people's expectations. Vgl [[Gap tussen eigen situatie en verwachting is constant 20071121211040]]

Also costly to run at all. If this is to increase efficiency of a corp or individual it needs to be energy efficient too. Otherwise doing it yourself is the more efficient option. AI is bound to the same laws of nature as us. [[AI heeft dezelfde natuurwetten 20190715135542]] Hiding away the inefficiency in a data center's footprint and abstracting into a service fee doesn't change that dynamic ultimately.

Again it's just a promise, which seems to be the AI mantra at every step.

multi step is what they're for no? Automator can do better than agents at this time it seems.

Exactly. All promise no delivery yet. It may work if the other side is equally automated, but if it's human or a dumb web form it won't. It also reveals on the side of the human demonstrator a big lack in reflecting on their own preferences that the AI should attach to its choices.

Vgl Phillips voice automation train tickets in 90s. 'Where do you want to go' 'It's not for me but for my mom' 'Destination not found: mom'

Note this is only 'nice' from the buyer's perspective. The 'phone call' to the shop still means having a human be subject to a computer call. It also probably means you don't care about what's being bought. No back story to e.g. a gift. Beware [[Spammy handelings asymmetrie 20201220072726]]. You automate 10 million things be sent, but need to be deleted by a human e.g.

Indeed. [[AI personal assistants 20201011124147]] https://www.zylstra.org/blog/2020/10/narrow-band-digital-personal-assistants/ We should start with the personal here, wrt automation, not the AI to get to quicker results: [[small band AI personal assistant]] where the personal limits the range of possible inputs for a task and the range of acceptable outputs for a task, leaving a smaller area for an AI agent to do its thing in and thus be more effective.

Still, how much of that is already available to automate on-device? 'routine tasks automated' is not in need of AI. What are examples?

Agents are prompt chains that include fetching info (params!) from elsewhere for their function. vlg [[Standard operating procedures met parameters 20200820202042]] I wonder how you generalise them, other than 'go buy/book', and when you do if they are above what on-device automation can do. In the end individuals need to be able to set the params/boundaries of any agent, make it their own agent, rather than some corps agent. What I see at consumer facing level is not aiding consumers but aiding corps reduce human interaction with consumers. Agents should increase agency, is the lithmus test.

for - stats - comparison of cognitive powers - AGI AI agents vs human researcher

stats - comparison of cognitive powers - AGI AI agents vs human researcher - 100 million AGI AI researchers - each AGI AI researcher is 100x more efficient that its equivalent human AI researcher - total productivity increase = 100 million x 100 = 10 billion human AI researchers! Wow!

for - progress trap - debate - nobody is discussing the dangers of such a project!

progress trap - debate - nobody is discussing the dangers of such a project! - Civlization's journey has to create more and more powerful tools for human beings to use - but this tool is different because it can act autonomously - It can solve problems that will dwarf our individual or even group ability to solve - Philosophically, the problem / solution paradigm becomes a central question because, - As presented in Deep Humanity praxis, - humans have never stopped producing progress traps as shadow sides of technology because - the reductionist problem solving approach always reaches conclusions based on finite amount of knowledge of the relationships of any one particular area of focus - in contrast to the infinite, fractal relationships found at every scale of nature - Supercomputing can never bridge the gap between finite and infinite - A superintelligent artifact with that autonomy of pattern recognition may recognize a pattern in which humans are not efficient and in fact, greater efficiency gains can be had by eliminating us

Vgl how I discussed an application this morning that deployed multiple AI agents as a interconnected network, with each its own role. [[Rolf Aldo Common Ground AI consensus]]

https://deadline.com/2022/11/wme-promotes-eric-reid-to-partner-1235182887/

https://www.lydiawills.com/agency.html

Agents don't have free will but they are influenced by their surroundings, making it hard to predict how they will respond, especially in real-world contexts where interactions are complex and can't be controlled.

the Function-as-a-Service offering often have multiple fine-grained updateable code modules (functions) running within the same vm, which comes pretty close to the Erlang model.

then add service mesh, which in some cases can do automatic retry at the network layer, and you start to recoup some of the supervisor tree advantages a little more.

really fun article though, talking about the digital matter that is code & how we handle it. great reminder that there's much to explore. and some really great works we could be looking to.

Jones, Callum J, Thomas Philippon, and Venky Venkateswaran. ‘Optimal Mitigation Policies in a Pandemic: Social Distancing and Working from Home’. Working Paper. Working Paper Series. National Bureau of Economic Research, April 2020. https://doi.org/10.3386/w26984.

C’est l’exposé de la position défendu par l’auteur. L'argument commence par " nous croyons" il s'agit d'un jugement personnel. Les auteurs pensent qu'avec l'évolution de la technologie de la réalité virtuelle, beaucoup de personnes vont choisir cette forme de sexualité . Cependant, aucune recherche scientifique n'est cité pour confirmer leurs affirmations.

Marx refers to the thought experiment, common in economics, which is sometimes called Robinson Crusoe economics.

Doing "Robinson Crusoe economics" consists in imagining what can be learned, if anything, from a one agent economy that will provide insight into a real world economy with lots of agents.