soleveloper

They don't lead on latency nor quality; but their execution was superb

While possible to commit, I'd still loose the comments themselves, and the commit will be at least per changeset, and not connected ro a specific changed section.

Roughly speaking, I'd be happy if plannotator would persist something similar to github PR reviews combined with Google docs comments & suggestions.

I have roughly the same workflow, also with plannotator - which I like a lot - and haven't used or felt the need to use _plan mode_ for at least 3-4 months.

Then telling Claude to work on a document, the instruction is kept to its core.

Now when bcherny explicitly mentioned that it merely adds a single line - it explains why I don't need it.

What may be concerning about "super plan" mode from the creators (or a skill, for that matter) - is that tuning the amount of effort, and how much deep to dig - may become too hard, as it will interfere with several embedded paragraphs explaining what to do, how to do, where to do, etc'.

What I do look for is even better plannotator ability to track changes, combining historical comments (like Google docs), and git blame of several "generations" before current reviewed doc.

So now every already written kernel can be re-written in Rust and have competitive performance to the cpp version?

If so, that's really big.

And to add the Next natural strp - custom codegen for simulating gpu compute and memory without Nvidia gpu.

I think the meaning of can't hallucinate in this model is that the type won't be hallucinated.

So if the generated schema is for a tool call for calculator, then the numbers will be valid numbers for sure (and not random words).

To me, it looks similar to BNF schema already introduced and implemented few years ago: generally speaking - it limits the next token that is allowed to be generated, probs are drawn from a subset tokens.

(tbh, I'm not sure why it didn't pick up as a more standard interface to LLMs, as it made a lot of sense back then, and now.)

Is there a list of all LG tracking services and external DNS endpoints?

I'd just block them - and keep local streaming and remote control working

edit: just found out WebOS doesn't support DoH/DoT so nextdns won't work.

I wonder if one of the public dns providers got LG blocklisted natively with specific IP

It reminds me a site where you'd pick a point on map and see where you'd get to in 15/30/etc minutes, including walking iirc.

Then you could even pick *two* points in map and see their intersection in time period, which was great for finding places to meet friends.

Yes, discord as an example would be awesome, exactly what I thought.

Is this back of envelope pricing include the traffic/bandwidth of the readers?

That could easily be 10-100x of number of messages.

This solution together with a cheap/free caching layer (especially for non members/writers) could be amazing.

BTW, a classic example would be an hn mirror. ;)

Sounds great, and documentation is very clear.

So - in theory - something like a massive chat client, discord like, can be implemented via this solution? And what would be the pricing of such a solution. Cheap-serverless-discord

> They may only have bought themselves 6 more months of time given their purported burn rate

If they had only ~6 more months they (+auditor) had to issue a warning. The 6 is not a hard number, AFAIK, but surely a point where it must be reported.

So honestly, I doubt it's the case.

Well, the EU regulated USB-C and it affected the whole smartphones world.

It is time to standardize EV batteries like wheels: 5-10 mainstream types & competition on quality vs. price vs. range.

Regulator help is needed here.

Makes sense - This is very similar to fine tuning a down stream task in encoder-decoder architecture (~Bert style)

Was just reading the title and thinking it's a new and upgraded image gen model from Google.. Anyone else?