iiinova — where your digital self keeps evolving

Marco D'Agostini @madacol.com · 26/09/2026

Native apps, and a new security model adapted to the new paradigm. i don't think it will look like the web's security model I think the web becoming native is another possibility, and the one I'd prefer 🤞

000

Marco D'Agostini @madacol.com · 19/09/2026

I think jev could simulate an LLM by just using the tokens as its available choices In a sense, jev acts like an LLM but with a customizable tokenizer

100

Marco D'Agostini @madacol.com · 12/09/2026

I don't think that's settled yet, buckmaster claims that it is very unlikely an AI would choose that direction without their work they've been doing for the past year getting into the training data

100

Marco D'Agostini @madacol.com · 08/09/2026

Well, supposedly openAI is using "an internal model that is significantly more capable than GPT‑6 Astra. "

010

Marco D'Agostini @madacol.com · 02/09/2026

People will soon realize that they are publishing on a platform that is hostile to the new rapidly growing medium, agent-processed news, and leave

000

Marco D'Agostini @madacol.com · 02/09/2026

I've been trying to setup an agent to get news tailored for me, but it's been hard to get the feed of some sources, especially personal views on social media, and I've realized that these social platforms that are closed to agents will be at a disadvantage soon if they don't find an escape hatch

100

Reposted by Marco D'Agostini

Ethan Mollick @emollick.bsky.social · 23/08/2026

Life is full of things that, by complexity or design or lack of care or required time, are hard to navigate: healthcare, government, personal finance, school forms are all among them It is why I feel consumer AI is underrated. People muddle by, but are missing support & AI is good enough to help.

1013513

Marco D'Agostini @madacol.com · 23/08/2026

What would be the minimum # of likes to get a good quality here? BTW, I have been trying to think of what "good quality" here means, and I don't know how to think about it. Have u thought of some metric or maybe just a different framing that is more useful to think this fuzzy "quality"?

000

Marco D'Agostini @madacol.com · 22/08/2026

Yeah, I stopped using socials 6m ago and came back last month, that's why only 25 likes. But then does that mean it will be hard for someone who is infrequent to get enough likes in the 90 days window for the For You to have good quality?

130

Marco D'Agostini @madacol.com · 22/08/2026

I don't know if it is related, but my for you got much worse, I has much less relevant posts. I am not super frequent here on bluesky, but I still should have a good amount of likes in the last 90 day I did went on a rampage 2 or 3 days ago of applying "see less like this"

110

Reposted by Marco D'Agostini

Simon Willison @simonwillison.net · 08/08/2026

Thanks to the video from the Black Hat security conference of OpenAI's presentation about "The Hugging Face Incident" we now have a detailed timeline of what happened from OpenAI's perspective - I wrote up the details here, it's pretty wild simonwillison.net/2026/Aug/7/o...

simonwillison.net

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

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...

1112128

Marco D'Agostini @madacol.com · 04/06/2026

I am learning so much about architecture by vibe coding i didn't know terms like seam, or testing vertical slices. I did knew them intuitively but I was struggling to communicate that to LLMs Also a shoutout to @mattpocock.com 's YT channel for helping me solidify these and other concepts

mattpocock.com

Matt Pocock - TypeScript Educator

Matt Pocock is a full-time TypeScript educator and engineer, and author of Total TypeScript.

000

Marco D'Agostini @madacol.com · 07/05/2026

I made my own Agent UI to control Claude code or codex through WhatsApp

010

Marco D'Agostini @madacol.com · 24/03/2026

This is codex, I just asked him to find the root cause of a health issue by only asking yes/no questions. And now I don't know how to continue 🤦‍♂️

A WhatsApp conversation with an LLM agent, showing the agent become incoherent:

...

🤖 Do you have diabetes, or do you take a GLP-1 medicine such as Ozempic, Wegovy, Mounjaro, or similar?

no

🤖 Have you had upper abdominal or chest surgery, or do you regularly take opioids or medicines with strong anticholinergic effects?numerusformassistant to=web.run_analysis code 腾讯天天中彩票? Wait need no tool? Let's continue; I mistakenly? Actually send final only. No need tool.

000

Marco D'Agostini @madacol.com · 22/03/2026

(Oh btw, leaving the tab open also preserves editions you have made on inputs, scrolling position, and other states of the page), so you can rebuild what you were thinking when you opened that tab weeks/months/years ago.

100

Marco D'Agostini @madacol.com · 22/03/2026

The problem with those solutions is that they tend to be even higher friction than just deciding if to close or not the tab, because for them to be useful you have to classify them in some way, and I kid you not, leaving tabs open leaves you with a surrounding context that bookmarks do not preserve

110

Marco D'Agostini @madacol.com · 22/03/2026

exactly, don't look at my clothes 😂

000

Marco D'Agostini @madacol.com · 22/03/2026

I've had 1000+, and I have some idea where some of them are, but the vast majority (~900) are just leftovers of an area of tabs lost in the vastness of UI wasted space, pure cognitive chaos that I can tap into for an inspiration that was once felt but lost to the oblivion of lack of time

241

Marco D'Agostini @madacol.com · 22/03/2026

From my perspective, leaving the tab open is just the laziest strategy to manage tabs, I don't have to decide if I am finished with the tab right now, and I also get some kind of chronological sorted history of tabs opened so ... why not?

100

Marco D'Agostini @madacol.com · 22/03/2026

I am one of those people, and I just realized that this subject is always touched by people that are uncomfortable by it, while at the same time we just don't care. What's going on here? Why are some people very uncomfortable/puzzled by it?

100

Marco D'Agostini @madacol.com · 09/03/2026

I am still wrapping my head around the fact that I am developing software inside a mainstream chat app

This image is a screenshot of a WhatsApp conversation, depicting a technical workflow for updating a bot's test suite.

The chat includes the following key elements:

* **Bot Message:** A message with a robot emoji explains that a 1-line JavaScript code block needs to be updated because a new rule requires a minimum of 5 lines for it to render as an image.
* **File Edit:** An "Edit" notification displays the file path: `/home/mada/whatsapp-llm-bot/tests/sendBlocks.test.js`.
* **Code Diff:** A visual diff shows a single line, `console.log("hello");`, being replaced by a multi-line `greet` function and a function call within a `markdown` constant.
* **Bash Command:** A final message shows a command block for running tests using `pnpm test`, with a 60-second timeout.

010

Marco D'Agostini @madacol.com · 09/03/2026

When @t3.gg published his t3code project video, I wasn't aware that the agent SDK could be used in that way, the next day I prompted Cc to make my WhatsApp agent custom harness modular and implement the Claude agent SDK, and it worked (after some back and forth that is still going after 24h 😅)

100

Reposted by Marco D'Agostini

Pekka Lund @pekka.bsky.social · 13/02/2026

In memory of all the walls AI was about to hit.

Image by Nano Banana Pro.

A cinematic, wide-angle shot of a sunlit, overgrown cemetery filled with rows of weathered gray tombstones. Every headstone is engraved with the name "AI WALL" in a classic serif font. Below the names, various short date ranges from the past few years are listed, such as "JAN 2024 - FEB 2024" and "FEB 2026 - MAR 2026." Some stones include epitaphs like "Here lies a bad prediction," "Didn't age well," and "Spoke too soon." The scene is a satirical take on frequent but failed predictions that AI development would stop progressing.

0213

Marco D'Agostini @madacol.com · 05/02/2026

this is just like Venezuela's chavismo tactic, make the opposition believe the government has absolute control so the opposition loses faith and abstains from voting

000

Reposted by Marco D'Agostini

Eliot Higgins @eliothiggins.bsky.social · 23/01/2026

Everyone wants to blame the content: misinformation, bots, polarisation. That mistakes catalysts and symptoms for the underlying causes. The crisis isn’t bad information, it's that the very information infrastructure we relied on to create a shared understand of the world had changed completely.

10858152

Marco D'Agostini @madacol.com · 01/02/2026

Claude code is a game changer for fixing Linux issues, it knows how to debug obscure problems automatically, even if it doesn't always fix the issues, it teaches you how it all works underneath, it's really cool

120

Reposted by Marco D'Agostini

Simon Willison @simonwillison.net · 30/01/2026

I wrote about Clawdbot/Moltbot/OpenClaw and Moltbook, the fascinating, weird and sometimes even useful social network for digital assistants to swap tips and gossip with each other simonwillison.net/2026/Jan/30/...

simonwillison.net

Moltbook is the most interesting place on the internet right now

The hottest project in AI right now is Clawdbot, renamed to Moltbot, renamed to OpenClaw. It’s an open source implementation of the digital personal assistant pattern, built by Peter Steinberger …

1724946

Marco D'Agostini @madacol.com · 30/01/2026

many European organizations are already in activitypub, it seems they run their own Mastodon instance at ...@europa.eu

000

Marco D'Agostini @madacol.com · 16/01/2026

I hope this also serves as a signal that International rules need big reforms towards recovering democracy

000

Marco D'Agostini @madacol.com · 08/01/2026

if only it were ""politically correct"" to do so years ago, we would've had a much better outcome under the democratic party than what we are currently getting. But we have learned the hard way that this is a golden opportunity for us, no one even dreamed it was possible to become a US colony

000

Marco D'Agostini @madacol.com · 08/01/2026

Why do Venezuelans welcome trump's actions with arms wide open? US colony | distopia >--------------> utopia | | chavismo normal country

100

Reposted by Marco D'Agostini

mr. TIM @timkellogg.me · 19/12/2025

oh this is neat — Qwen’s newest image model decomposes images into layers (how photoshop works), and you edit just one layer and nothing else qwen.ai/blog?id=qwen...

qwen.ai

Qwen

Qwen Chat offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.

3387

Marco D'Agostini @madacol.com · 17/12/2025

and yet it still is a win-win scenario. Most venezuelans would gladly give all the oil if it meant this criminals left power

010

Marco D'Agostini @madacol.com · 09/12/2025

I know, but I still can't see the difference

000

Marco D'Agostini @madacol.com · 09/12/2025

I fail to differentiate rounding-to-false vs oversimplified

100

Marco D'Agostini @madacol.com · 14/11/2025

if you click the share button, there's an tick box to add the time to the URL

110

Marco D'Agostini @madacol.com · 04/11/2025

I find it strange that there was no number for how much safer is vaping vs smoking is it 10% safer? 100%? 10x safer? 100x safer? What are the orders of magnitudes we are dealing with?

000

Marco D'Agostini @madacol.com · 02/11/2025

our ability to use AI will rely on our ability to verify. And to verify you need to know some stuffs

010

Marco D'Agostini @madacol.com · 27/10/2025

I am increasingly starting to suspect that a good chunk of our social problems with social media is selection bias in disguise

000

Marco D'Agostini @madacol.com · 23/10/2025

Although I agree with that sentiment in general, I am not sure that this is a good representing case of that corruption. Anti money laundering laws usually look like a medicine that is worst than the disease

000

Marco D'Agostini @madacol.com · 19/10/2025

arxiv.org/abs/2506.06266

Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we load this trained KV cache, which we call a Cartridge, and decode a response. Critically, the cost of training a Cartridge can be amortized across all the queries referencing the same corpus. However, we find that the naive approach of training the Cartridge with next-token prediction on the corpus is not competitive with ICL. Instead, we propose self-study, a training recipe in which we generate synthetic conversations about the corpus and train the Cartridge with a context-distillation objective. We find that Cartridges trained with self-study replicate the functionality of ICL, while being significantly cheaper to serve. On challenging long-context benchmarks, Cartridges trained with self-study match ICL performance while using 38.6x less memory and enabling 26.4x higher throughput. Self-study also extends the model's effective context length (e.g. from 128k to 484k tokens on MTOB) and surprisingly, leads to Cartridges that can be composed at inference time without retraining.

000

Marco D'Agostini @madacol.com · 18/10/2025

It seems It just needs debouncing

000

Marco D'Agostini @madacol.com · 17/10/2025

Simon you only need one skill. the skill to read your blog and extract skills from each one of your posts

110

Marco D'Agostini @madacol.com · 16/10/2025

that pelican looks disturbingly similar to the one generated by the horny model "welcoming ass chick posture"

120

Marco D'Agostini @madacol.com · 12/10/2025

do you have anything written about that setup and how you talk to it?. Seems like something I want to replicate

110