
Dr Jevsky
94 posts


@steipete @clawsweeper How are you testing the quality of the review?
English

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

"No society in history has ever regulated itself into abundance."
Josh Wolfe@wolfejosh
Pretty CRAZY. one shot Claude code with a skill made this animated video of my essay with my voice. My input was the essay text and few APIs for image gen and voice. Less than an hour. 🤯 It has a few errors, pronunciations and images––all correctable with more prompts
English

@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

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

And yet Canada has an entire industry of activists and academics telling us that incarceration does not protect society from crime.
Nayib Bukele@nayibbukele
It’s a very simple concept, really.
English

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

@ListerLawrence Perhaps because range is a very important metric for EV’s and not for petrol cars
English

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

@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

@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

@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

@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


@blc_16 @AnthropicAI You have inspired me to save the world. I too will move into sales. God bless you
English

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

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

@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

@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









