jasperanders (@_asperanders) header
jasperanders (@_asperanders) profile picture
Joined April 2021
Photo by jasperanders (@_asperanders)Photo by jasperanders (@_asperanders)
I built .bdf to easily share html directly from my agents. I use Claude a lot to create html slides and documents, but sharing plain html with others is annoying. .bdf gives you a shareable link in a single prompt. give it a try: bdf.pub/
2
3
166
Replying to @JonasScholz19
I told you it’s not a good idea to build sliplane in php
1
1
33
Did you ever see someone flipping the sign of your loss, and achieve great results? Well, this summer, we did. Some papers (refs below) suggested to reverse the self-distillation loss, i.e, move away from the teacher. We wrote a blogpost on our investigation and our findings.
Self-distillation with privileged context shifts behavior and can hurt reasoning. Repulsion reverses the shift but becomes unstable. In our experiments, contrasting both signals improves reasoning while keeping training stable. Blog: self-distillation.github.io/…
1
4
14
1,231
Replying to @tldraw
@tldraw sorry, but wtf is going on? What are you doing and more importantly how? When can I rotate pigeons myself?
1
19
We needed VR teleoperation for intervention-based learning. So Aurel implemented the entire stack within two days. He now wrote an extensive blog post on the design decisions and embedded math for Pieper IK. We also open-sourced the code. Highly recommend for anyone into IK.
I implemented VR teleoperation for our robot arm because I wanted to do human intervention data collection and our GELLO leader arms didn’t allow it. I wrote all my learnings up and open-sourced the code…
4
3
26
3,845
jasperanders retweeted
es tut mir so leid, dass auf den Essigessenz-Flaschen immer Gemüse drauf ist…Bro…du kommst in keinen Salat…du entkalkst meinen Wasserkocher…
72
142
16
5,961
118,366
I am recently wondering how to pass the reverse turing test? how to prove i am a hunam after all?
5
It’s great that I did not put all my life savings into bdf.pub because just like that my moat would have gone poof
Building apps has never been easier. With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL. Rolling out to Business and Enterprise plans, before expanding more broadly.
26
me reviewing codex’s output after it worked for 16 hours straight
13
18
2
389
30,959
Nice! I‘m pulling that! I found HTML always a bit hard to edit and collaborate on. That’s why I built bdf.pub, an easy way to collaborate and share slides and any kind of HTML.
65
I think this is really cool! I think it would be nice to see a slide deck directly here. Have you thought about auth?
1
23
jasperanders retweeted
Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks. On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
515
718
419
6,013
1,989,049
Makes so much sense to share things this way in a AI native era.
I built .bdf to easily share html directly from my agents. I use Claude a lot to create html slides and documents, but sharing plain html with others is annoying. .bdf gives you a shareable link in a single prompt. give it a try: bdf.pub
1
16
4,009
Replying to @trq212
Nice! Can you share a link to the deck? You can tell Claude to publish it with bdf.pub and he will give you a shareable link
780
I built .bdf to easily share html directly from my agents. I use Claude a lot to create html slides and documents, but sharing plain html with others is annoying. .bdf gives you a shareable link in a single prompt. give it a try: bdf.pub
This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral teapawt.org/zan2434/status/2046982… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.
2
2
8
4,546
Replying to @karpathy
finally we can replace pdfs. And its even more shareable: after you have a local html you can tell you agent to publish it via bdf.pub, pretty nice!
23
Replying to @trq212
finally we can replace pdfs. And its even more shareable: after you have a local html you can tell you agent to publish it via bdf.pub/, pretty nice!
13
Fun weekend project: We simulated 900 shopping conversations with ChatGPT to find out how it thinks about running shoes. open.substack.com/pub/jasper…
59
Sharing our latest work: Reinforcement Learning via Self-Distillation We introduce Self-Distillation Policy Optimization (SDPO), an on-policy RL algorithm that turns feedback into dense, token-level learning signals.
4
7
4
58
12,219