Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Tag

anthropic.com

Post reply on HN
Print view View original

161–170 of 200 posts

Re: Claude Tag

#161

Post by theshrike79 »

Chyzwar wrote: post #126

Why Slack? Everything about this product sucks: bad video calls, no meeting recording, limited screen sharing, janky authentication, and predatory pricing. They shoudl just expose SDK/platform for people to build own integration with Discord/Teams/mattermost etc. This would allow for fine grained permisions control and speed up adoption. To large degree this is alternative for OpenClaw ?

Slack has enterprise features and billing. Discord does not.

People use Teams only because it's basically free when you get the M365 suite for your company, not because it's good or usable in any way.

Re: Claude Tag

#164

Post by mogili »

holografix wrote: post #146

Wowza this will be a token guzzler. Assuming Claude is parsing every message posted on multiple slack channels, compacting knowledge etc. Looks like Anthropic is progressing further into platform territory and conquering Agentic use cases left right and centre. If you’re building an agent platform for workforce productivity today, your best best is model agnosticism and focus on token cost control.

Token consumption on this is not a huge issue, I built this a few months ago for our company slack using claude agent sdk and most of the conversations/sessions were short lived. You don't generally tend to have long sessions with agents in Slack like you would if using in the terminal.

It was very useful to delegate things like create a ticket based on a discussion to Claude.

Re: Claude Tag

#166

Post by kylecazar »

deadbabe wrote: post #138
kylecazar wrote: post #132

Earlier quoted context omitted.

An admin scopes permissions on a per-channel basis. It doesn't allow external actions until an owner specifically provisions that tool for that channel. I think. But people can be invited to a channel after @Claude is provisioned. So yeah, I suppose you'll need to be deliberate about channel memberships.

Which is a bad pattern. Around here, you can be granted access to most channels just with vague reasons for why you need to be in there. This is a disaster. Culture will degrade. Suspicions will grow. Security theater.

Yeah, it may indeed require some new Slack processes and discipline. But, the alternative would be account linking (like GH). Your interactions would have responses from Claude that are only visible to you if others didn't have the required permissions. It would use your credentials, etc.

That would defeat the stated purpose of collaboration/shared context, it would essentially just be another surface for your private Claude sessions.

Just gotta either decide not to use it or use it and not be willy nilly about the Slack channels in which it's provisioned.

Re: Claude Tag

#167

Post by nijave »

theshrike79 wrote: post #159
nijave wrote: post #110

Earlier quoted context omitted.

Their "safety" system that arbitrarily flags things. Tons of examples of innocuous strings setting it off and sometimes with financial impact like the OpenClaw/hermes thing (just having the word "hermes" would insta deplete your quota and start charging you API rates in extra usage)

The hermes trigger was a bug and they fixed it in a few hours. But bad news carries far and wide.

I read the Github issue. They also initially refused a refund until the whole thing blew up

Here's another one https://github.com/anthropics/claude-code/issues/52809

It's definitely not an isolated incident

Re: Claude Tag

#168

Post by cyanydeez »

threecheese wrote: post #131

WRT “Claude learns over time” - this is the biggest gap for me in the current system. As I scale my usage of Claude at work, I observe that it’s quite bad at distinguishing what it should “learn” (memorize) from experimental or just wrong data. It builds and builds on a foundation of sand, making sometimes hidden assumptions and turning them into actionable insight thats just not correct. It recently wrote an entire…

I think memory has very little benefit from non-curated sources. its just a source of halucinatd context and bloated. I think focused work on context removal integrated in the tools would be much better.

Especially in the thinking models; with opencode qnd local LLM. i've got no choice at times but to review the thought traces and if I could go in and correct a few of them before they go do what stupid shit they're hallucinating, I'd reach much better outcomes then fightint with them.

Re: Claude Tag

#169

Post by claw-el »

holografix wrote: post #146

Wowza this will be a token guzzler. Assuming Claude is parsing every message posted on multiple slack channels, compacting knowledge etc. Looks like Anthropic is progressing further into platform territory and conquering Agentic use cases left right and centre. If you’re building an agent platform for workforce productivity today, your best best is model agnosticism and focus on token cost control.

Fundamentally, Anthropic is a token merchant (it is higher quality than other models, but still token merchant), so it will find any excuse to make you spend more tokens, and not even try too hard to help you save on tokens.

The whole ‘inline visualization’ thing is another great example. You want to know about this new concept on Claude? Why don’t I generate this new ‘inline visualization’ for you to learn it even if it doesn’t significantly help you at all…

Re: Claude Tag

#170

Post by mhitza »

mogili wrote: post #164
holografix wrote: post #146

Wowza this will be a token guzzler. Assuming Claude is parsing every message posted on multiple slack channels, compacting knowledge etc. Looks like Anthropic is progressing further into platform territory and conquering Agentic use cases left right and centre. If you’re building an agent platform for workforce productivity today, your best best is model agnosticism and focus on token cost control.

Token consumption on this is not a huge issue, I built this a few months ago for our company slack using claude agent sdk and most of the conversations/sessions were short lived. You don't generally tend to have long sessions with agents in Slack like you would if using in the terminal. It was very useful to delegate things like create a ticket based on a discussion to Claude.

> You don't generally tend to have long sessions with agents in Slack like you would if using in the terminal.

You have to check the announcement fineprint. As long as they advertise it as proactive it needs to keep up to date with all the ongoing discussions. And I believe that means all group messages. Wouldn't that make sense?

From the announcement

> follows along with its channel, it builds more context about the work

> And Claude can even automatically learn from other Slack channels and data sources, if it’s granted permission.

And the additional "ambient" mode also seems to imply that it will work by itself in background tasks to check (I assume) in some scheduled fashion what stale topics it needs to reengage.

Post reply on HN