Dr Jevsky

94 posts

Dr Jevsky

Dr Jevsky

@Doktorjevsky

Katılım Mart 2022
119 Takip Edilen2 Takipçiler
Peter Steinberger 🦞
5.6 Terra high is underrated. Switched @clawsweeper (GitHub review bot) to it and it's ~40% faster overall with negligible quality loss. Better than 5.5 on all counts. Massively cheaper. (Tried xhigh but that negates perf wins, didn't make a noticable difference in review evals)
English
144
102
2.6K
362.5K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@jack You are one agent away from automating yourself. Keep going
English
0
0
1
9
jack
jack@jack·
i’ve shifted from telling agents what to do, to asking them what to do, and pulling the best thread.
English
1.1K
1.2K
19K
1.5M
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@petergyang Doesn’t this just reflect that they are good at arguing any point? What is in it for them to have an opinion, really?
English
0
0
0
149
Peter Yang
Peter Yang@petergyang·
One thing that still annoys me about even the best AI models and agents: They’ll give an overconfident opinion. Then if you push back even a little, they’ll usually reverse it right away. It makes me feel like they weren’t thinking that hard in the first place. A good human teammate might change their mind too, but they’ll at least explain why or have a more principled approach to their thinking. Maybe there’s a way to fix this with a system prompt?
English
198
23
543
50.5K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@jkenney The graph shows no correlation? How can you not see that?
English
0
0
0
11
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@thdxr How is this problem any different from any problem that the LLM solves for you?
English
0
0
1
224
dax
dax@thdxr·
i have low conviction on model routers - very open to changing my mind but this is a snapshot of my current thoughts - i don't think it's good to not be aware of what model you're using. coding with LLMs is a skill you develop and getting a feel for models is part of that - people (at scale) don't have this skill right now which is why a lot of companies are complaining that people are using expensive models for dumb things. a model router promises to solve this without the user having to do anything but i think the issue is missing feedback loops to the user. id rather we figure out how to help users get smarter - i dont even know how much you can model route when factoring in things like prompt cache. only so much you can do - their effectiveness is a bit exaggerated by the same dynamic that's impacting everything AI. so many companies desperately searching for opportunities and trying anything. model routing is the one thing models labs cannot do so everyone is jumping on it
English
141
41
999
95K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@ListerLawrence Perhaps because range is a very important metric for EV’s and not for petrol cars
English
0
0
0
6
Lawrence Whittaker
Lawrence Whittaker@ListerLawrence·
I’m not an EV hater, but the problem with EV’s that no one talks about is: When the range gets to 0 in an EV the car just stops. In some cases they can’t even be pushed… When the range gets to 0 in a Petrol or Diesel car, you have a built in grace period of 30-40 miles that isn’t shown on the car’s trip computer. Thus range anxiety doesn’t exist in an ICE vehicle. Why don’t EV’s do that?
English
1.1K
13
528
275.5K
Harry Doyle
Harry Doyle@KevinDools·
@Doktorjevsky @mungowitz Great point that anyone capable of elementary math can figure out. My point is pretty simple. What you’re suggesting isn’t practical.
English
1
0
0
9
Michael Munger 🏖️🔪👨‍🍳
Apparently the theory is that restaurant owners SHOULD, morally, lose money. So only those wealthy enough to lose a LOT of money should own restaurants. Why would I own a restaurant in the first place, then? Wealth of the owner is a complete non sequitur.
English
57
6
48
10.8K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@KevinDools @mungowitz Idk which point you are trying to make? I simply made the point that higher wages would necessitate higher prices (and not handouts from the restaurant owner).
English
1
0
0
6
Harry Doyle
Harry Doyle@KevinDools·
@Doktorjevsky @mungowitz Hmmm…wonder if “some” restaurants closing would affect the job market. Sounds fun having fewer options and more crowded/expensive restaurants too. A winning philosophy all the way around. Well done 🤓
English
1
0
0
11
Dave W Plummer
Dave W Plummer@davepl1968·
@ewarren ie: You got yours, now pull the ladder up. I presume you won't be disgorging yourself of your previous trading profits on principle?
English
8
1
221
3.1K
Elizabeth Warren
Elizabeth Warren@ewarren·
It's time for us to ban stock trading for all members of Congress, for the vice president, and for the president. Period.
English
7.9K
1.7K
6.4K
616.3K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@zeeg Rick Moranis makes a comeback
English
0
0
0
79
David Cramer
David Cramer@zeeg·
who's gonna play Dario in the inevitable film adaptation?
English
19
1
38
6.5K
Aleph
Aleph@woke8yearold·
Aleph tweet media
Spencer Baggins@bigaiguy

A French engineer who lives quietly in Paris has spent 30 years writing software that the entire internet now runs on without knowing his name. He wrote the code that streams every YouTube video, every Netflix show, every TikTok clip. He wrote the code that runs the virtual servers underneath AWS, Google Cloud, and Microsoft Azure. He calculated more digits of pi than anyone in history. He has no Twitter. He has no marketing. He just keeps shipping. His name is Fabrice Bellard. Here is the story, because almost nobody outside the systems programming world knows what one man has built. Fabrice was born in 1972 in Grenoble, France. He studied at École Polytechnique, the top French engineering school. He never went to Silicon Valley. He never built a startup empire. He just wrote code. In 2000 he started a project called FFmpeg, an open-source multimedia framework for encoding, decoding, and streaming video. He was 28. The project did one thing nobody else had done well. It handled every video and audio format that existed, in one library, on every operating system. He led it himself for years. Today FFmpeg is the invisible engine of the internet. YouTube uses it. Netflix uses it. VLC uses it. Chrome and Firefox use parts of it. Every Android phone, every iPhone, every smart TV, every video editing tool you have ever touched runs FFmpeg somewhere underneath. If you have watched a video on a screen in the last 20 years, Fabrice's code processed it. He was not done. In 2003 he started QEMU, a machine emulator and virtualizer. He wrote it solo until version 0.7.1 in 2005. QEMU lets you run any operating system on any other operating system. It became the foundation of modern virtualization. KVM, the Linux kernel hypervisor, runs on top of QEMU. Every major cloud provider, AWS, Google Cloud, Microsoft Azure, IBM Cloud, runs virtual machines on infrastructure built around it. The Quick Emulator is the most cited piece of cloud infrastructure code on Earth. He kept going. In 2001 he won the International Obfuscated C Code Contest with a small C compiler that grew into TCC, the Tiny C Compiler. TCC can compile and boot a Linux kernel from source in under 15 seconds. In 2004 he calculated the most digits of pi ever computed at the time, using a personal desktop computer and an algorithm he derived himself called Bellard's formula. In 2011 he wrote a complete PC emulator in pure JavaScript that runs Linux in your browser, a project called JSLinux that engineers still cannot believe is real. In 2019 he released QuickJS, a small but complete JavaScript engine that fits where V8 cannot. In 2021 he released NNCP, a neural network based lossless data compressor that immediately took the lead on the Large Text Compression Benchmark. Then he turned his attention to large language models. He built TextSynth Server, a web server with a REST API for running LLMs locally. He released ts_zip and ts_sms, compression utilities that use language models to compress text and short messages at ratios traditional algorithms cannot reach. He released TSAC, a very low bitrate audio compression system. In December 2025 he released Micro QuickJS, a new JavaScript engine for microcontrollers, separate from QuickJS, designed for environments with almost no memory. Fabrice co-founded a telecom company called Amarisoft in 2012, where he serves as CTO. Amarisoft builds 4G and 5G base station software used by carriers and labs around the world. He has been running it for over a decade while continuing to ship personal projects from his own home page at bellard dot org He has no Twitter. He has no Instagram. He gives almost no interviews. His personal website is a flat list of projects with no styling, no fonts, no marketing copy. Just titles and links. A quiet French engineer who never moved to Silicon Valley wrote the code that quietly runs the internet. He is still shipping.

ZXX
23
1.4K
20.6K
747.2K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@tszzl What are you even talking about? The “not nice words” are used for IPO marketing by the leading AI labs. They are deliberately spreading fear. Change your handle to loon
English
0
0
1
843
roon
roon@tszzl·
the frontier labs don’t have “comms problems”. reality right now has a comms problem. what is happening is a little scary and there’s no nice words anyone could say, especially not those profiting from it, that’ll make it feel that much better
English
189
181
3.5K
377.8K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@blc_16 @AnthropicAI You have inspired me to save the world. I too will move into sales. God bless you
English
1
0
2
2.9K
Ben Cohen
Ben Cohen@blc_16·
I’ve decided to leave @AnthropicAI Never thought I’d say this so soon. The pursuit of AGI has truly been my life’s work but something more important has emerged. In 1942, hundreds of America’s best scientists made huge sacrifices and joined the Manhattan Project to protect this nation against immense evil. Today, America faces a similar danger. Over the last few years sparks of AGI have been felt across the world. In order to protect this great nation against the threat of AGI ending up in the hands of evil, I have decided to join the modern day Manhattan Project. I’m excited to announce that I’ll be joining (and moving into the office) @UseCorgi as a sales development representative!
English
743
334
9.6K
2.4M
Aram Hăvărneanu
Aram Hăvărneanu@aramh·
I was never a gamer, but I lost all interest in non-PC games when controllers became wireless. The latency is just too bad. I don't understand how anybody can play anything on a wireless controller. I also lost all interest in PC games when they went 3D.
English
13
0
34
4.9K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@emollick A productivity gain would surely make EBITDA per employee increase?
English
0
0
0
4
Ethan Mollick
Ethan Mollick@emollick·
We have, as far as I can tell, no good tests of the productivity impact of the autonomous coding tools that appeared starting in December 2025. Every paper out there is from prior to the Claude Code/Codex revolution. A huge gap in our knowledge about what is happening in coding.
English
81
48
697
43.9K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@mcuban Why do you think these incentives don’t exist right now?
English
0
0
0
2
Mark Cuban
Mark Cuban@mcuban·
We should federally tax Tokens at the Provider level. Not a lot. Less than 50c per million tokens. It will accomplish 4 things (at least ) 1. It will push the big AI players to optimize tokenization, caching , routing and localization Which will 2. Reduce energy usage. Saving them in energy costs more than what they paid in tax and reducing strain created by the growth in energy consumption Which will 3. Generate maybe 10 billion dollars a year to start, but over the next ten years could grow 30x to 100x Which will 4. Create a source of funding to pay down the federal debt or deploy, in response to the things AI brings that we don’t expect or don’t like At some point the models will pass it on to customers. Of course. That’s ok. Customers will have the ability to choose between providers. Or to do everything using open source models locally. Thoughts ?
English
2.1K
254
4K
1.2M
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@benlandautaylor The same people who send people into space are not allowed to build e.g libraries and that is why they don’t? Are you retarded?
English
0
0
1
676
Ben Landau-Taylor
Ben Landau-Taylor@benlandautaylor·
Reading another "Why don't rich guys build libraries like Carnegie anymore" article. It's because that's illegal now. In most cities you can barely even build an apartment. Never mind the psychoanalysis, it's just against the law.
English
89
422
7K
323.4K
Dr Jevsky
Dr Jevsky@Doktorjevsky·
@CWood_sdf Yes I guess that you at best can have a small input/output quotient if your intent is derivable from the context/codebase (isn’t that what we call boilerplate?).
English
0
0
0
1.2K
Chris Wood
Chris Wood@CWood_sdf·
i love how people are saying "if we write a sufficiently detailed specification, the agent can write all our code" do you know what writing a sufficiently detailed specification that deterministically maps to what a computer's actions is? it's coding
English
353
1.6K
20.9K
581.9K