Xorlev

Sure it is.

The prefill is the only blocking part, and you can prefill the whole context up to the point where they diverge, then prefill each question and decode the one token in parallel for each question.

If you batch vLLM calls with the same prompt prefix to the same process, it'll deduplicate the prompt prefix across batched requests (+/- the block size) and decode in parallel for each.

That's with a vanilla LLM. If you modify the LLM you can pull that in-graph, but it isn't really necessary.

> you really don’t feel the need to seek validation from other people in your life.

This might be confusing the lack of need for validation with the lack of need for other people. Sure, taking confidence from your partner is wonderful but it's not "seeking validation" to maintain other relationships.

Putting everything on one person can quickly become codependency and enmeshment. At some level some codependency/enmeshment is inevitable ("healthy interdependence") when you spend your time with one person, however it can also be very unhealthy.

You can lose your own identity, and end up putting all your needs on the other person. That makes conflict difficult, distance difficult, and you lose your support network.

I think Friday demos are really cute, and a healthy relationship can certainly touch on all areas, but it's important to invest in both other relationships (friends/family/partners) AND yourself. Investing in time with yourself means investing in your hobbies, doing things just for you and maintaining that individual identity.

GitHub solved the original "code collaboration" problem, and now it's a default easy way to outsource repo management. It also has the most integrations. A lot of companies grew up using GitHub.

GitHub was, once upon a time, quite stable. Things have changed: more features, more usage, and automated agents.

> i.e., claude code and similar, things are either prefill-bound

When accounting for prefix caching, this greatly accelerates each turn. Barring large file reads, prefill still isn't the bottleneck vs. decoding reasoning tokens. Script-writing too.

This is especially true during exploration phases when traversing through directory trees and grepping files, you're talking about a few hundred tokens/turn.

Not a Java implementation, but the original game was written in Java. Later, Microsoft bought Minecraft and rewrote it (Bedrock edition) which runs on Xbox, tablets, etc. But, the community writes mods in Java.

Now both exist and get roughly the same feature set now, but the Java version remains popular given the vast variety of mods and servers.

Google was already fairly profitable when Gmail was started, and did a considerable amount of capacity planning.

It was also invite-only for a loooong time.

> Free forever for teams up to 5. Unlimited search, unlimited history.

I understand the strategic value of offering unlimited features to differentiate from competitors like Slack, might drive some amount of anxiety. Buyers may question long-term sustainability or fear undisclosed "shadow" caps.

Since engineering limits are inevitable to prevent abuse (especially on free accounts), it might be better to set specific, generous expectations upfront. For example, 2 years of freeform search plus unlimited "tagged" (i.e. Decision Inbox) search. This avoids the skepticism that comes with promising "no limits" forever. It also avoids the trap of needing to announce a change later with predictably negative reactions.

If you do want to offer unlimited, then planning ahead with hard-to-hit-unless-you're-trying messages/hr limits might help you tame growth and avoid abuse. My initial thought when seeing unlimited anything is "I could write a filesystem on top of that" - especially if you allow attachments. :P

There are, and often times they're stuck in a loop of presenting decks and status, writing proposals rather than doing this kind of research.

That said, interpreting user feedback is a multi-role job. PMs, UX, and Eng should be doing so. Everyone has their strengths.

One of the most interesting things I've had a chance to be a part of is watching UX studies. They take a mock (or an alpha version) and put it in front of an external volunteer and let them work through it. Usually PM, UX, and Eng are watching the stream and taking notes.

This is often (though not always) blanket statement.

Logs are always generated, and logs include some amount of data about the user, if only environmental.

It's quite plausible that the spellchecker does not store your actual user data, but information about the request, or error logging includes more UGC than intended.

Note: I don't have any insider knowledge about their spellcheck API, but I've worked on similar systems which have similar language for little more than basic request logging.

Do you have a source for that? I'm not denying it, just curious to read more.

You'd think so, but for datacenter workloads it's absolutely common, especially if you're just scheduling a bunch of containers together. Computation also doesn't happen in a vacuum, unless you're doing some fairly trivial processing you're likely loading quite a bit of memory, perhaps many multiples of what your business logic is actually doing.

It's also not as easy as GB/s/core, since cores aren't entirely uniform, and data access may be across core complexes.

Except it's also trivial to buy or produce tables of pre-hashed emails, so this cloak of "oh we don't know who you are, it's a hash!" is usually just lipservice.

Android also reaps permissions that haven't been used recently. In the case of location, Android prompts for renewal even if it has been used recently.

There is no war in Ba Sing Se.

Just saying it doesn't make it true. Twitter has a long way to go to regain advertiser confidence, and Blue is barely a footnote.