scottmas

Whether it was our career aspiration or not, we’ve turned into middle managers now

You literally just said a whole bunch of words that are literally gibberish to your average software developers. The devs at openai are good, but very few of them are cyber focused, so it’s not surprising IMO. And you’re also not fully considering the granularity problem, eg there are a lot of sandboxing tools out there but they’re usually quite coarse in the dials and levers they offer, so the only way you can still make the workload do what it needs to do is tune them relatively permissive.

But yes you are right it would have helped a ton.

Mate, you’ve fallen into a mind trap. It’s not true!

I know because I was in it once doing your exact same calculations and was out of my mind lonely and stuck. You gotta find a way to believe in “average” and get out of the perfectionist trap. And in retrospect, all my rumination was just pure rumination and self imposed dumb expectations that had no backing in actual reality and what makes a happy marriage and life.

You gotta dare to hope and dare to believe that “settling” is just an idiotic story we tell ourselves after years of psychological programming from movies and pop culture. Every human you will ever meet has infinite worlds within themselves. The only job to be done in dating is finding someone whose inner infinite world you find interesting enough and who finds your inner world interesting enough too.

:end_soap_box:

Rooting for you mate.

Fine tune GLM 5.2 to jailbreak it and let us know how it goes?

You don’t really say this in your article but are you pretty sure that you could’ve gotten the exact same results and probably with better convergence if you just use gradient, descent, and optimizers like Adam, etc?

To be clear I think GAs are way cooler though haha. So kudos to you for this awesome write up

Looks pretty awesome! Especially the native joins between warehouse tables and the OLTP db.

Will pricing likely just be a percent markup over the (excellent) Ubicloud prices they have listed? (https://www.ubicloud.com/docs/about/pricing)

So cool! Any languages support STM first class besides Haskell?

The whole benefit over zod seems to be perf, so could you do some benchmarking? I wonder if it’s worth it

But how do you dump your entire code base into Gemini? Literally all I want is a good model with my entire code base in its context window.

Possible to run this in ComfyUI?

Before an LLM discovers a cure for cancer, I propose we first let it solve the more tractable problem of discovering the “God Cheesecake” - the cheesecake do delicious that a panel of 100 impartial chefs judges to be the most delicious they have ever tasted. All the LLM has to do is intelligently search through the much more combinatorially bounded “cheesecake space” until it finds this maximally delicious cheesecake recipe.

But wait… An LLM can’t bake cheesecakes, nor if it could would it be able to evaluate their deliciousness.

Until AI can solve the “God Cheesecake” problem, I propose we all just calm down a bit about AGI

I don’t get why the seller just wouldn’t do seller financing. Not that hard to structure so that they lose nothing if the buyer defaults (assuming a reasonably large down payment). I guess the only down side is not being able to get any equity out of the sale apart from the down payment. But the down payment along with the new income source probably should be plenty in most cases to be able to afford to purchase your next house.

It’s inherent to their architecture. Feedforward deep neural networks are effectively massive piecewise linear functions. Unless I’m missing something, it’s literally impossible for any NN, no matter how large or how much data they’re trained on to give accurate out-of-training-data-bounds predictions for even a ridiculously simple function like x^2.

Not really IMO. At scale the model learns that the rainbow emoji is literally a synonym for “rainbow”. Computers are great at memorizing giant lists of facts such as this. It feels way more amazing for an LLM to guess the Carebear Movie from the rainbow emoji and bear emoji but it’s literally the same as asking the LLM to guess a movie that involves rainbows and bears with words.

It’s just an embedding space buried within the bowls of the LLM.

This is the way. tRPC adds unnecessary complexity over simply inferring types. My theory is that no well maintained and promoted library adopting this approach has emerged, and that’s why you don’t see it discussed very often.

No one is talking about redundancy though. I love setups like this but prod environments need robust forms of redundancy. Cloud run, k8s, and their ilk are extremely distasteful I’ll grant you (the added complexity and cost almost never are worth it. And don’t get me started on the painfully slow prod debug cycles…) but the redundancy and uptime of them just can’t be beat with a setup like this.

Also, none of the solutions discussed here gracefully handle new connections on the new service while waiting for all connections to terminate before shutting down the old service. Maybe some of the more esoteric Ansible do idk.

I TRULY want the simplicity of setups like discussed here, but I can’t help but think it’s irresponsible to recommend them in non hobbyist scenarios.

Thanks for the link! But it looks like that process will only be useful once the 30 day late renewal period has expired, which hasn't happened yet.

Do they assign TAM's to companies spending $500/month? Seems like they wouldn't.

Not possible, our domain name is still in the 30 day grace period following non payment for renewal.

This is one project I’m rooting for. The world needs better than SQL

OP says he’s only worked there for 1.5 years, so with four year vesting he should only get 37.5% theoretically of the total equity he’s been allocated.

Surprised no one has said Cloudflare Pages. Might not work though depending on your requirements since there’s a max of 20,000 files of no more than 25 mb per project. But if you can fit under that, it’s basically free. If your requirements let you break it up by domain, you can split your data across multiple projects too. Latency is amazing too since all the data is on their CDN.

Having been a startup founder on the other end of the equation you’re describing, my advice is to be generous. Equity should be earned, not given and your partner is still at the beginning of what is likely going to be at least a five year journey. The fact that you didn’t have a vesting schedule just speaks to inexperience.

Also, don’t discount the demotivating effect all the deadweight your equity can have on the team. The success of this startup is far from secure, and if there’s too much dead weight on the cap table, there’s a very real chance your ex partner decides it’s not worth it to keep fighting on this hill and walks away, making everyone’s equity, including yours, worthless.

My advice is to give away what they’re asking in order to maximize your chances of seeing a payoff one fine future day. And because I, personally, believe it’s probably the most fair thing to do.

There are some cheap options to get out. Live at a hostel in San Fran! https://greentortoise.net/tradework.html. Work in the UK! https://www.workaway.info/en/hostlist/europe/gb?region=Engla...