thinking about knowledge management @knowcenter, student of Software Developement at TU Graz, mobile devices (iPhone :P) and web 2.0 geek
47.068424,15.448110
Joined September 2007
- Tweets3.2K
- Following1.8K
- Followers1.3K
- Likes1.1K
j_simon retweeted
What if an optimizer could think & react while a neural network trains?
MIT researchers developed OPAL: a deep learning optimizer powered by an AI agent that watches the training dynamics & rewrites its own source code as training goes. It improves model performance across vision & language tasks, invents specialized schedules, & develops strategies to prevent loss spikes & escape overfitting: tinyurl.com/yfkekat2
Try it out for yourself: tinyurl.com/mttj5exh
j_simon retweeted
recommended reading. i have many feelings about this.
rikiyat.github.io/blog/weigh…
j_simon retweeted
New blog post: AI has no copyright? Tell that to the software industry technollama.co.uk/ai-has-no-…
j_simon retweeted
New work on Training Foundation Models with a Single Algorithm:
Paper: arxiv.org/abs/2610.40564
Code, Models: yudasong.github.io/unified-t…
This work introduces Unified Training, a framework that unifies pretraining, midtraining, supervised fine-tuning and RL under a single maximum-likelihood objective. Building on MaxRL, it enables static data and RL-generated data to be trained together within the same system.
Empirically, Unified Training improves accuracy and compute efficiency, generalizes better to harder reasoning problems, and reduces forgetting.
Interestingly, reusing data across training stages can improve performance even when conventional staged training fails. It also produces models that adapt more effectively to new tasks, leading to stronger continual learning.
See an excellent thread by @yus167.
j_simon retweeted
Amortizing Sequential Experimental Design in Reasoning LLMs
paper: huggingface.co/papers/2610.2…
j_simon retweeted
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.
💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.
🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.
Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.
Read more from our team and customers 👇:
j_simon retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
🤖 Made with AI
j_simon retweeted
"Mathematical Theory of Deep Learning" is an excellent free resource for anyone interested in the mathematical structure underlying modern deep learning systems. The book introduces the theory of deep neural networks through approximation theory, optimization theory, and statistical learning theory, three of the central pillars of the field.
What makes it particularly interesting is its attempt to balance rigor with accessibility, focusing on the essential ideas needed to understand modern AI systems without sacrificing mathematical depth. Despite this clarity of exposition, the book is clearly oriented toward a specialized audience.
It is also an enormous cultural contribution and an extremely valuable free resource for students, researchers, and anyone interested in studying deep learning more rigorously.
arxiv.org/abs/2407.18384
j_simon retweeted
Bypassing #EU #AgeVerification using their own infrastructure.
I've ported the Android app logic to a Chrome extension - stripping out the pesky step of handing over biometric data which they can leak... and pass verification instantly.
Step 1: Install the extension
Step 2: Register an identity (just once)
Step 3: Continue using the web as normal
The extension detects the QR code, generates a cryptographically identical payload and tells the verifier I'm over 18, which it "fully trusts".
This isn't a bug... it's a fundamental design flaw they can't solve without irrevocably tying a key to you personally; which then allows tracking/monitoring.
Of course, I could skip the enrolment process entirely and hard-code the credentials into the extension... and the verifier would never know.
Hacking the #EU #AgeVerification app in under 2 minutes.
During setup, the app asks you to create a PIN. After entry, the app *encrypts* it and saves it in the shared_prefs directory.
1. It shouldn't be encrypted at all - that's a really poor design.
2. It's not cryptographically tied to the vault which contains the identity data.
So, an attacker can simply remove the PinEnc/PinIV values from the shared_prefs file and restart the app.
After choosing a different PIN, the app presents credentials created under the old profile and let's the attacker present them as valid.
Other issues:
1. Rate limiting is an incrementing number in the same config file. Just reset it to 0 and keep trying.
2. "UseBiometricAuth" is a boolean, also in the same file. Set it to false and it just skips that step.
Seriously @vonderleyen - this product will be the catalyst for an enormous breach at some point. It's just a matter of time.
j_simon retweeted
young people who want to learn programming still exist! (sharing the screenshot with their permission).
as corporate has decided we no longer need juniors, i think one function of OSS projects could be to keep the junior -> senior pipeline working. here's how i'll try to do it.
j_simon retweeted
we as software engineers are becoming beholden to a handful of well funded corportations. while they are our "friends" now, that may change due to incentives. i'm very uncomfortable with that.
i believe we need to band together as a community and create a public, free to use repository of real-world (coding) agent sessions/traces. I want small labs, startups, and tinkerers to have access to the same data the big folks currently gobble up from all of us. So we, as a community, can do what e.g. Cursor does below, and take back a little bit of control again.
Who's with me?
cursor.com/blog/real-time-rl…
j_simon retweeted
9 interesting observations from my conversation with Mitchell Hashimoto (@mitchellh, creator of Ghostty, founder of HashiCorp):
1. Vagrant was created because dev environment setup was an unbillable time sink at a consultancy. At the Ruby on Rails shop where Mitchell worked, jumping onto another client’s project could waste half a day. This inspired building Vargant.
2. Terraform won, despite being 7th to market. Terraform won through relentless conference presence, community building, and a better developer experience — not timing.
3. HashiCorp had no real business for four years and their first commercial product was a full-on failure. The initial product, Atlas, required customers to adopt the entire HashiCorp stack. It was a hard sell. HashiCorp pivoted to selling individual services like Vault, and this approach proved to be a winner.
4. VMware almost bought HashiCorp for ~$100M, and Terraform would have not happened if it did. VMWare took took the offer to their board, where they rejected to buy with a single vote. Mitchell said that Terraform probably never would’ve existed if the VMWare purchase went through.
5. Mitchell’s new rule for building software: always have an agent running in the background doing something. He kicks off tasks before leaving the house — research, edge-case analysis, library comparisons — so work progresses while he drives or is away.
6. Open source is moving from “default trust” to “default deny” — and Mitchell thinks that’s how it should be. This is because AI makes it trivial to create plausible-looking but incorrect and low-quality contributions. As he put it: “open source has always been a system of trust. Before, we’ve had default trust. Now it’s just default deny.”
7. Git and GitHub may not survive the agentic era in their current form. Agents cause so much churn that merge queues become untenable, branches proliferate, and repos balloon. Mitchell compares the needed shift to Gmail’s revolution for email: “We’re at the Gmail moment for version control... never delete, archive everything.”
8. The best engineers Mitchell ever hired had boring, invisible backgrounds. No GitHub contributions, no public profiles, companies you’ve never heard of. “Every moment you spend on social media is taking away from something else... the best engineers are the ones that context-switch the least.”
9. Mitchell’s advice for AI-skeptical engineers: start by reproducing your research, not your code. As he puts it:
“There’s a lot of people like, ‘I don’t want it to write code for me.’ But just delegate some of the research part.”
He uses agents for library comparisons, edge-case analysis, and deep research — not just code generation. Mitchell: “You don’t need to pick up on the ‘it must replace you as a person’ kind of propaganda.”
Watch the full episode here: youtu.be/WjckELpzLOU
Other platforms and transcript: newsletter.pragmaticengineer…
j_simon retweeted
Been doing a lot of UI testing on iOS and Android recently and really like @maestro__dev
Super simple, great DX with emulators etc and easy to write and verify tests.
j_simon retweeted
Person 1: We got so much VC money, we gotta burn it faster to raise more
P2: But we already susidize tokens
P1: We gotta do better.
P2: Hold my beer cto.new/blog/why-we-raised-5…
