It seems like we do know the year it was painted fairly reliably, but we don't know that it was Michelangelo specifically that painted it (the article exudes more confidence that I would give based on the inherent uncertainty of these identifications).
Why? There were other talented people who produced masterful works at an early age. From the same time as this there's a Dürer self-portrait, also aged 12-13:
I came here to agree with you but then I had the good sense to read the original page which is at the Met (https://www.metmuseum.org/exhibitions/listings/2009/michelan...), and has a lot of background on this painting, including that it WAS actually painted from an existing image (https://en.wikipedia.org/wiki/The_Temptation_of_St_Anthony_(... - worth a look to compare), so my primary skepticism "how could a kid even come up with that" makes a lot more sense that he had an existing image he was copying.
The article/video only points to this being proven by research done by Giorgio Bonsanti. If you're curious, you'll have to investigate that angle.
It is frustrating that the article is so coy about the evidence around the premise of the article! But, this website and the youtube video this article is based around both lean more towards pop than investigative.
Gary Marcus (probably): "Hey this LLM isn't smarter than Einstein yet, it's not going all that well"
The goalposts keep getting pushed further and further every month. How many math and coding Olympiads and other benchmarks will LLMs need to dominate before people will actually admit that in some domains it's really quite good.
Sure, if you're a Nobel prize winner or PhD then LLMs aren't as good as you yet, but for 99% of the people in the world, LLMs are better than you at Math, Science, Coding, and every language probably except your native language, and it's probably better at you at that too...
I think you must be talking about something else, the Delta bot in discussion here has about 2500 ELO and basically crushes anyone who isn't a professional chess player.
This is your assertion made without any supportive data or sources. It's nice to know your subjective opinion on the issue but your voice doesn't hold much weight making such a bold assertion devoid of any evidence/data.
This times 100000. I've been using Mac OS since 1992 and this version (both IOS and MacOS) has had me pulling my hair out more than every other version, and note, I did use OSX 10.0!
The first thing I did with Tahoe was go into the System Preferences to try and turn off as much as possible of the new UI because it's the biggest regression in Mac OS history (at least since I've been using Macs).
I used to mock Windows for the Explorer UI and general GUI experience, now I think I prefer using my Windows 10 PC over my Mac. It's just such a fucking mess, so inconsistent, shitty performance (even on brand new macs and phones), is actively harder to grok, much harder to use for my elderly parents, and doesn't even look "cooler" or "better" in any way. It's just worse on every possible metric, and made me start wondering about an Android phone, which has never happened since I bought an original iPhone.
I am and have been the ultimate Apple fanboy since 1992, but this release fucking sucks balls. I hope you're listening Apple.
Do we really need another vibe-coded LLM context/memory startup?
Do the authors have any benchmarks or test to show that this genuinely improved outputs?
I have tried probably 10-20 other open source projects and closed source projects purporting to improve Claude Code with memory/context, and still to this date, nothing works better than simply keeping my own library of markdown files for each project specification, markdown files for decisions made etc, and then explicitly telling Claude Code to review x,y,z markdown files.
I would also suggest to the founders, don't found a startup based on improving context for Claude Code, why? Because this is the number 1 thing the Claude Code developers are working on too, and it's clearly getting better and better with every release.
So not only are you competing with like 20+ other startups and 20+ other open-source projects, you are competing with Anthropic too.
This. Exactly this. Even relatively well working tools (from my experience and for my project types) like Agent OS are no guarantee, that Claude will not go on a tangent, use the "memory files" the framework tells it to use.
And I agree with your sentiment, that this is a "business field" that will get eaten by the next generations of base models getting better.
I mostly agree with this, if the goal were “better persistent memory inside Claude Code,” that wouldn’t be very interesting.
For a single agent and a single tool, keeping project specs and decisions in markdown and explicitly pointing the model at them works well. We do that too.
What we’re focused on is a different boundary: memory that isn’t owned by a specific agent or tool.
Once you start switching between tools (Claude, Codex, Cursor, etc.), or running multiple agents in parallel, markdown stops being “the memory” and becomes a coordination mechanism you have to keep in sync manually. Context created in one place doesn’t naturally flow to another, and you end up re-establishing state rather than accumulating it.
That’s why we're not thinking about this as "improving Claude Code”. We’re interested in the layer above that: a shared, external memory that can be plugged into any other model and tools, that any agent can read from or write to, and that can be selectively shared with collaborators. Context created in Claude can be reused in Codex, Manus, Cursor, or other agents from collaborators - and vice versa.
If one already built and is using one agent in one tool and is happy with markdown, they probably don’t need this. The value shows up once agents are treated as interchangeable workers and context needs to move across tools and people without being re-explained each time.
If markdown in a git repository isn’t good enough for collaboration, then why would any plugged in abstraction be better?
You imply you have a solution for current wholistic state. For this you would need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost).
That narrative becomes harsher once you pivot to “general purpose agents” because you’re then competing with every existing knowledge work platform. So you’ll shift into “unified context for all your KW platforms” - where presumably the agents already have access (Claude today can basically go scrape all knowledge from anywhere).
So then it becomes an offering of “current state” in complex human processes and this is a concept I’m not sure any technology can capture; whether it’s across codebases (which for humans we settled on git) and especially not general working scenarios.
And I guess this is where it becomes a unified multi-agent wholistic state capture. Ambitious and fun problem.
| need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost).
I agree. We are looking at some metr benchmarks, not expecting a simple answer to this, but do you have any in mind you find compelling?
Not really. But, You can go viral again with a "Coding Agents with memory build better software using less tokens" showcasing how you benchmarked a "twitter rebuild" -
1. Setup Claude Code to build some layers of the stack
2. Setup Codex to build others.
In one instance equip them both with your product. Maybe bake in some tribal knowledge.
In another instance let them work raw.
In both instances, capture:
- Time to completion
- Tokens spent
- Ability to meet original spec
- Subjective quality
- Number of errors and categorize between the layers, to state something like "raw-claude's backend kept failing with raw-codex's frontend" etc
I imagine this benchmark working well in your favor.
right. I stopped reading at "ENSUE_API_KEY | Required. Get one at [dashboard](link to startup showing this is an ad)"
First thought: why do I need an API key for what can be local markdown files. Make contents of CLAUDE.md be "Refer to ROBOTS.md" and you've got yourself a multi-model solution.
Main objection to corporate AI uptake is what are you gonna do with our data. The value prop over local markdown files here is not at all clear to even begin asking that question.
It blows my mind that anyone can consider Stranger Things to be great anything. It's utter dross. It's like our standards have dropped massively over the last 50 years in almost every way, in literature, music, journalism, politics, movies, and TV.
Yeah it feels slow and laggy to me too and I'm not on an old laptop. Running on a M3 Macbook Pro here. I definitely notice the difference between using something like Ghostty (Rust based - super fast) and Toad (Python).
It's obviously way slower though. Also the point stands, it's written in a low-level, performance-oriented language. The author of Toad could have written it in Rust, Zig, C++, etc, but chose Python instead. He valued ease of development versus performance and the result is we get a laggy terminal.
I know for a fact that Textual can generate an entire frame in less than a 60th of a second. Any lag you see has nothing to do with the choice of language. A TUI just doesn’t require that much number crunching to use a low level language.
I’d be interesting in knowing what platform and terminal you observed the lag, when testing Toad.
Vim has a terrible user experience though. There's a reason everyone stopped using it as soon as they possibly could and moved to other text editors. Now the only vim users are the 60 year old+ greybeards who try to convince everyone they're such morons for not using it.
Stop trying to convince people to use vim, it sucks, it's got a terrible ux, it's not intuitive, it's overly complicated, hard to learn, arcane, and looks like ass.
I disagree, but I'm a 60 year old+ greybeard who has managed to get a bunch of other devs addicted to vim. My real goal is to keep the key bindings popular enough that I won't have to reprogram my muscle memory before I shuffle off.
reply