101–110 of 118 posts
Earlier quoted context omitted.
I feel like this is the right way to do it. Especially if you're using your own credits. Unless it's obnoxiously long task. So often it'll cut off just as it's about to finish.
Buys $10 worth of credits. > Codex, translate the entire PostgreSQL codebase to idiomatic Rust, make no mistakes.
The day after that, Zig broke compatibility, fix that.
Earlier quoted context omitted.
I talked with Hochreiter about 1.5y ago they should go for it and properly scale xLSTM to LLMs, not just playing around with few B params for experiments. They felt like they are too late to the game to get investment and traction. So much for European ambitions I guess...
Yes, but how would it have been if the EU governments just piled on, subsidized whoever had reasonable qualifications who wanted to try, straight-up funded accelerator development so that the chips don't just become investment in US AI companies, straight up built the supercomputers for training, straight up offered access to groups that had previously had reasonable success in training some model. I don't think it w…
Earlier quoted context omitted.
Your tokens should defiently have expiry times on the range that you would need to login again.
I would prefer a 999 year login cookie. A well designed browser stores the cookies with similar security to the built in password manager anyway
Cookies can also be queried programmatically, whereas passwords need to have the users auto fill active and interact with the input element
Most extensions have effectively full access to your cookies, not to your passwords - which is a real attack vector (session exfiltration) which is actively being used by had acteues
There are ofc server set cookies which are not programmatically queryable, but that's not the norm (and they're still visible via the developer tools, so the core statement remains untrue)
Agentic coding is what's most relevant to software engineers, but so is speed, which is a real usability issue right now. Third-party inference providers like Fireworks have bridged the gap for some previous releases.
It's exciting to see the open weights frontier becoming the norm. Competing on having the frontier model is going to be an increasingly difficult business.
Earlier quoted context omitted.
I would prefer a 999 year login cookie. A well designed browser stores the cookies with similar security to the built in password manager anyway
That's not true, you need to provide a password to read the passwords saved in the browser whereas cookies can be read without any hassle from the developer tools Cookies can also be queried programmatically, whereas passwords need to have the users auto fill active and interact with the input element Most extensions have effectively full access to your cookies, not to your passwords - which is a real attack vector (…
Earlier quoted context omitted.
So I am likely coming from a completely different world because I use entirely self hosted models - but is it really common in your workflows to just wait for 12 minutes without any feedback? I am constantly watching my model and following the path it’s taking and cutting it off or steering it if it’s headed down a dead path. I was just curious if this is really common to just have no feedback for 12 minutes?
I recently had GPT 5.6 work on something for 54 minutes while I went to sleep
Today we needed to migrate to a cheaper CI/CD provider and do a better robotic for a particular task. GPT-5.6 Sol.
Earlier quoted context omitted.
Frustratingly none of the coding harnesses seem to default to just firing up a docker container with the working directory mounted and letting the AI run wild inside the container.
You can get that working for yourself trivially. My agent environment now has 3 different kinds of compute abstractions, 3 different agents and a nascent workflow engine in it. It works how _i_ want, which is really refreshing.
Earlier quoted context omitted.
I would prefer a 999 year login cookie. A well designed browser stores the cookies with similar security to the built in password manager anyway
That's not true, you need to provide a password to read the passwords saved in the browser whereas cookies can be read without any hassle from the developer tools Cookies can also be queried programmatically, whereas passwords need to have the users auto fill active and interact with the input element Most extensions have effectively full access to your cookies, not to your passwords - which is a real attack vector (…
Misleading statement, essentially untrue.
> Most extensions have effectively full access to your cookies
False.
> There are ofc server set cookies which are not programmatically queryable, but that's not the norm
That is the norm for login cookies.
> and they're still visible via the developer tools,
This is irrelevant to the argument.
Personal anecdote: I exhausted my Claude usage yesterday so I decided to spend 20$ to try Kimi while I was at it. Logged in, paid, downloaded Kimi Code, set it to use K3 and prompted something along the lines of: "Check this repository and find all the settings that can be passed as input related to hardware, I/O, thread control or networking. Produce a report". It thought for about 12 minutes and then told me I had…