haneul

How does this differ from Hermes / Openclaw / Vellum?

I didnt think about it this way, but it would be helpful to have infra around reputation in the same way email has them.

And, it would be nice to have unsubscribe lists in the uBlock Origin style.

NX again??

This isn't the first time their plugin has led to RCE...

How are you able to get to $300/hr productively? (I’m assuming this isn’t fast mode tax).

Works perfectly installed as part of a server and at mentioning you there. Direct DMs are finicky in my experience.

Except for pro and plus users in the EU eh…

I still use it.

We have it as a data analyst that’s been trained via exemplar queries and MD about the underlying databases.

It also does ad creatives analysis and overall paid marketing spend analysis, including delivering briefs and conversing with stakeholders about things such as cross-ad-platform deduplicated cost of customer acquisition.

In general it is used to lower the technical bar required for cross-domain collab.

Interesting, another case of removing HT improving performance. Reminds me of doing that on Intel CPUs of a few gens ago.

There were also really good financing deals during Covid. Net for me after all costs after resale was $1k for the years I owned the car (the 2nd gen).

But I got in near the bottom and got out before the market for it dumped.

Even in a product as technically wonderful as Temporal, we can have relatively simple oversights like this that lead to cross tenant leakage.

If anyone is more familiar with Temporal, is there a way clients could have had internal defense in depth that guards against tenant leakage at the provider (Temporal) level?

My codex CLI didn’t notice version bump available, but I manually did pnpm add -g @openai/codex and 5.3 was there after.

As someone who doesn't keep track of the influencer scene at the moment because I am way addicted to building...

You should totally give Claude Code a try. The biggest problem is that it is glaze-optimized, so have to work at getting it to not treat you like the biggest genius of all time. But when you manage to get in a good flow with it, and your project is very predictably searchable, results start to be quite helpful, even if just to unstuck yourself when you're in a rut.

Hah that's pretty fun. I got tossed about by the animated hands for a few, but grabbed a 194 after that.

Dunno about the trigrams though, mostly it's on the "token group" level for me - either the upcoming lookahead feels familiar or it doesn't, and I don't much get bothered by the specific letters as much as "oh I don't have muscle memory on that word, and it's sadly nestled between two easy words, so it's going to be a patchy bit of alternating speed".

Love this news! Amazing by Bereket!

I wonder if a Lexus/Toyota Acura/Honda Lamborghini/Audi OpenAI/Microsoft marketing split isn't in the best interests of tech giants going forward since LLMs are nondeterministic, unlike the deterministic nation-states they've built up till now...

Don’t dangle the man - enrich him with your advice!

Yea the data market from discord bots is quite a thing. Really concerning, imo.

> tin foil can disrupt mind control

You're not weaponizing Gell-Mann amnesia against us are you?

I suppose it disproves embodied, fully meat-space god if sound?

> In plain language:

> No matter how sophisticated, the system MUST fail on some inputs.

Well, no person is immune to propaganda and stupididty, so I don't see it as a huge issue.

Hmm you can tweak fine these days without messing up context. But, I run in “ask mode” only, with opus in claude code and o3 max in cursor. I specifically avoid agent mode because, like in the post, I feel like I gain less over time.

I infrequently tab complete. I type out 80-90% of what is suggested, with some modifications. It does help I can maintain 170 wpm indefinitely on the low-medium end.

Keeping up with the output isn’t much an issue at the moment given the limited typing speed of opus and o3 max. Having gained more familiarity with the workflow, the reading feels easier. Felt too fast at first for sure.

My hot take is that if GitHub copilot is your window into llms, you’re getting the motel experience.

Monkeytype is better than keybr imo. More options (eg coding modes), actual zen mode, and doesn’t break above 149.5 wpm like keybr does (or did, haven’t been there in 2 years).

Naw there are tricks you can use to pipeline these things so that apparent latency is under 500ms even with significant game state history awareness, and also to interrupt ongoing but freshly out of date commentary.

I couldn’t get it under 250ms though (for rocket league), but the tech should be better now than 2024.

Have done an interactive commentator for rocket league that is also simultaneously your duo partner. Works quite well. This was in October 2024 so the tech is there and even better now.

Sqlalchemy definitely is more verbose.

Hmmm any specific syntax examples of pain points in Sqlalchemy? Having used both, they feel similar to me so I’d love your view!

Is pretty equivalent to alembic autogenerate, no?

Why moving away from Python at that threshold?

Any reading on the topic you could point me to? Whenever I head about vestigial DNA, I’m reminded of the preserved wetlands which forced the roads to arc the long way around it. And in so doing, structurally affected traffic despite no cars ever going inside its bounds.

I guess what I’m wondering how we can be sure that structure is function but non-coding structure has no function and exerts no selective pressure - isn’t the Golgi apparatus analogously “non-coding”?

> So GitHub might just choose to ignore the notice for React, get sued, and win, all without losing the safe harbor.

It wouldn't be React getting the notice. It would be say, someone forking React, then adding a pull request with some clearly DMCA-violating material.

Then, if downstream B DMCA shutdown doesn't affect upstream A's availability, there's still the question of A normally still having access to B's non-merged commits even in the case of B's deletion. So, A should still be access the DMCA-violating material.

And, if A's access to B's non-merged, DMCA-violating commit is truly revoked without affecting A otherwise... why can't we have a "Strong Delete" button on GitHub? Would seem they'd have to have "Strong Delete" functionality to comply with downstream B hitting DMCA.

Basically, I'm feeling either a violation of principle of least astonishment, or a violation of "strong-DMCA".

Unless this is to support a feature in Git/GitHub that I am too noob to understand. :shrug: