devcycle
905 posts
devcycle
@dev__cycle
looking for better software and bike rides
sf Katılım Kasım 2023
223 Takip Edilen36 Takipçiler
@tszzl @mattparlmer do you think OpenAI takes that risk more seriously than Anthropic
English
I finally understand why couple separated between SF and Mountain View is considered Long distance Relationship
English
@dev__cycle @deepfates you have to find and defeat one of us in hand to hand combat, or get a 1 on your KPOs for two consecutive years
English
this is why people will pay an extra $1000 per month to live in San Francisco instead of Oakland
English
@indif4ent @theo cyber is never symmetric
defender has to be 100%, attacker only has to find one hole
English
@initjean Mythos is just a myth until it's publicly accessible. otherwise anthropic needs to shut d f**ck up.
English
@jayendra_ram this is the outcome you fundamentally will get between any 2 companies where one has a moral stance and the other doesn't
English
absolutely 100% true
David Cramer@zeeg
vendor-specific chatbots are broken by design that means the Sentry agent, the Linear agent, and any others you might have in Slack they are fine for some point situations, they're nice to get started with, but agents with generalized access outperform them in every single scenario some weeks ago we built an internal Slackbot, gave it access to a bunch of systems (Sentry, GitHub, Linear, Notion, etc), and its capabilities overnight far exceed these other bots "Oh cool Linear can now search your code bases" - our bot did that on day one, and then could push that information wherever it needed to go. Its useful to the point where I now discourage use of things like the Linear bot because it _creates worse outcomes_. this also goes beyond the simple generalization of access: we can customize it. we throw in skills-as-runbooks, templates, etc and the outcomes once again incrementally improve if your org hasnt already built a general purpose bot internally you should. if you need inspiration ours is open source on GitHub (albeit fairly unstable still) github.com/getsentry/juni…
English
@bcherny @sickdotdev you don't need the full output pasted
it's been like this for months. not always, but regularly.
have an intern play nice on X. you fix claude as a product, which means dario to remediate the mistakes he's made in compute, fundraising, product integrity, and public relations.
English
@zeta_globin the alani nius are solid, definitely need to be cut w sparkling water tho
English
@ryanvogel for some reason they haven't published this feature much but it solved it for me
#automatic-caching" target="_blank" rel="nofollow noopener">platform.claude.com/docs/en/build-…
English
anthropic really just said no YOU manage the cache, not us
ClaudeDevs@ClaudeDevs
Useful tip to cut time-to-first-token on longer prompts in the API: pre-warm the prompt cache. Send your system prompt before the user prompt. Claude writes it to the cache, but skips generating any output. When the real user request lands, it'll hit a warm cache.
English