Related posts
Ismail Ghallou x.com
Start by open-sourcing your models and sharing the weights then
The the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
19 September
11 September
9 September
7 September
6 September
-
Their words
The market cap weights make sense relative to the fundamentals.
2 September
1 September
-
Their words
In this case, however, the agents did not copy their weights, attempt to procure replacement compute, or take other steps that would be rational to take if their objective was to survive shutdown. So while the agents in the OpenAI-Hugging Face Incident were rogue, they were not truly sovereign.
19 August
14 August
-
Their words
At the end of the day, this type of safety barely matters when true open-weights are coming.
12 August
9 August
26 July
22 July
-
Their words
I genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and scan/hack in most networks. This is only surprising because you assume OpenAI has sounder sandboxes.
20 July
-
Their words
Whereas aerobic exercise on that kind of intensity spectrum we just talked about seems to particularly benefit the gray matter which includes the hippocampus. Resistance training seems to particularly benefit the white matter.
15 July
7 July
17 October 2025
From one piece Andrej Karpathy — “We’re summoning ghosts, not building animals” 2 beliefs, in the piece's order there
-
Their words
anything that's in the weights it's kind of like a hazy recollection of what you read a year ago anything that you give it as a context uh at test time is directly in the working memory
-
Their words
These models don't really have this distillation phase um of taking what happened, analyzing it, obsessively thinking through it, um basically doing some kind of a synthetic data generation process and distilling it back back into the weights
11 March 2025
10 January 2025
-
Their words
Increasing the incentive and technical ability of AI companies to have good security is a very high priority, and in my view even more urgent than safety (though that’s also very important).
20 December 2024
-
Their words
If you can’t control where AI weights go (i.e., prevent leaking or theft), you can’t govern the technology.
8 November 2024
-
Their words
This is especially severe for open weight models, where deployment is essentially irreversible and mitigations can’t be improved later.
19 June 2024
-
Their words
It’s less about access to a model’s weights, it’s more access to compute that is putting the world in more concentration of power and few individuals. Because not everyone’s going to be able to afford this much amount of compute to answer the hardest questions.
18 March 2024
-
Their words
We want to put increasingly powerful tools in the hands of people for free and get them to use them. I think that kind of open is really important to our mission. I think if you give people great tools and teach them to use them or don’t even teach them, they’ll figure it out, and let them go build an incredible future for each other with that, that’s a big deal.
13 September 2023
From one piece Self-exfiltration is a key dangerous capability 2 beliefs, in the piece's order there
-
Their words
If a model was capable of self-exfiltration, it would have the option to remove itself from your control.
Self-exfiltration is a key dangerous capabilityaligned.substack.com
-
Their words
Moreover, model exfiltration is likely impossible to reverse.
Self-exfiltration is a key dangerous capabilityaligned.substack.com
15 March 2023
2 February 2022
-
Their words
Combining these three pillars yields a number of unusual, even uncomfortable views about ethics. I feel this discomfort and don't unreservedly endorse this approach to ethics.
1 October 2020
Nothing matches.
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.