Angel Chen ▄ ▀
@ideosyncretic.com
Web dev, design, UI/UX • Currently indie-hacking promptbible.ai with @andric.dev • LLMs ∩ tools for thought • Previously built ops admin tools at startups
Much decision-making is tacit or qualitative. Making our OODA loops more legible is the first step towards observability & steerability. AI systems might help us codify this nebulous process. But how will it be trained to do this, and on what data? We don’t have good primitives or tooling for this.
I don’t really want to prompt an AI system.
Instead I want it to passively watch what I do as I do things, talk to me to understand what I’m thinking as I do them, and progressively learn from me.
Over time, it should understands tacitly what it’s like to make certain decisions, and then do them.
Instead I want it to passively watch what I do as I do things, talk to me to understand what I’m thinking as I do them, and progressively learn from me.
Over time, it should understands tacitly what it’s like to make certain decisions, and then do them.
December 19, 2024 at 6:28 AM
Much decision-making is tacit or qualitative. Making our OODA loops more legible is the first step towards observability & steerability. AI systems might help us codify this nebulous process. But how will it be trained to do this, and on what data? We don’t have good primitives or tooling for this.
Reposted by Angel Chen ▄ ▀
The article I most want to read right now is a detailed breakdown of prompt engineering project from somebody who hand-wrote their own simple automated evals and then used those to iterate on a prompt over time, measuring the impact each change had on their eval score and shipping an improved app
November 28, 2024 at 2:40 PM
The article I most want to read right now is a detailed breakdown of prompt engineering project from somebody who hand-wrote their own simple automated evals and then used those to iterate on a prompt over time, measuring the impact each change had on their eval score and shipping an improved app
We used the new
@inngest.com test helper library together with @vitest.dev, works smoothly so far! ✨
github.com/inngest/inng...
(clerkDeletedAt is our own tombstone flag using event timestamp as proxy—doesn't actually exist on Clerk because the whole record gets deleted there)
#buildinpublic
@inngest.com test helper library together with @vitest.dev, works smoothly so far! ✨
github.com/inngest/inng...
(clerkDeletedAt is our own tombstone flag using event timestamp as proxy—doesn't actually exist on Clerk because the whole record gets deleted there)
#buildinpublic
November 7, 2024 at 5:21 PM
We used the new
@inngest.com test helper library together with @vitest.dev, works smoothly so far! ✨
github.com/inngest/inng...
(clerkDeletedAt is our own tombstone flag using event timestamp as proxy—doesn't actually exist on Clerk because the whole record gets deleted there)
#buildinpublic
@inngest.com test helper library together with @vitest.dev, works smoothly so far! ✨
github.com/inngest/inng...
(clerkDeletedAt is our own tombstone flag using event timestamp as proxy—doesn't actually exist on Clerk because the whole record gets deleted there)
#buildinpublic
Today: updating our webhook integration tests (going from NextJS route handler -> @inngest.com step fn).
Yesterday: manual tests, collating notes+samples of Clerk webhook event payloads which differ from docs (as do the libraries’ exported types) to send to support.
#buildinpublic
Yesterday: manual tests, collating notes+samples of Clerk webhook event payloads which differ from docs (as do the libraries’ exported types) to send to support.
#buildinpublic
November 6, 2024 at 4:13 AM
Today: updating our webhook integration tests (going from NextJS route handler -> @inngest.com step fn).
Yesterday: manual tests, collating notes+samples of Clerk webhook event payloads which differ from docs (as do the libraries’ exported types) to send to support.
#buildinpublic
Yesterday: manual tests, collating notes+samples of Clerk webhook event payloads which differ from docs (as do the libraries’ exported types) to send to support.
#buildinpublic
Collapsible threads would be neat (there’s a feature request for this on GitHub)
Turned on threaded mode right away. Big fan of this UI.
I do wish that chained replies were the same level, and replies to those were threaded though.
I do wish that chained replies were the same level, and replies to those were threaded though.
it looks like this and it's under Settings > Thread Preferences
November 6, 2024 at 2:08 AM
Collapsible threads would be neat (there’s a feature request for this on GitHub)
Reposted by Angel Chen ▄ ▀
Would you look at that. GitHub has added support for Bluesky handles on your GitHub profile.
November 1, 2024 at 3:03 AM
Would you look at that. GitHub has added support for Bluesky handles on your GitHub profile.