Hacker News: spruce_tips

New comment by spruce_tips in "MIT Technology Review has confirmed that posts on Moltbook were fake"

spruce_tips — Tue, 10 Feb 2026 14:59:42 +0000

Yea I knew embeddings I just didn’t quite understand it in OPs context. Makes sense, thanks

New comment by spruce_tips in "MIT Technology Review has confirmed that posts on Moltbook were fake"

spruce_tips — Tue, 10 Feb 2026 13:05:00 +0000

sorry - what do you mean by embeddings in your last sentence?

New comment by spruce_tips in "Vouch"

spruce_tips — Tue, 10 Feb 2026 02:08:49 +0000

https://github.com/JoeBerg8/tollbooth

this was part of a little saas tool i was building (since retired it) so spent some time today having an LLM help me pull it into a headless service. far from perfect but sharing anyway. details in readme!

New comment by spruce_tips in "Vouch"

spruce_tips — Tue, 10 Feb 2026 02:08:45 +0000

https://github.com/JoeBerg8/tollbooth

New comment by spruce_tips in "Vouch"

spruce_tips — Tue, 10 Feb 2026 02:08:33 +0000

https://github.com/JoeBerg8/tollbooth

New comment by spruce_tips in "Vouch"

spruce_tips — Tue, 10 Feb 2026 01:37:18 +0000

no one paid me but didnt really have this running for very long on my inbox. was really just a poc. and you're right - the human side is weird. surprisingly hard to solve the "real human, not spam, that's also an email address you see for the first time" scenarios, which there are many of - even with LLMs

New comment by spruce_tips in "Vouch"

spruce_tips — Mon, 09 Feb 2026 01:46:16 +0000

I built a side project to solve this for myself that’s basically an inbox toll system. It funnels emails from unknown senders into a hidden mailbox and auto replies to the sender with a payment link. After the sender pays, the email gets released to recipient’s main inbox. Recipient can set custom toll amounts, whitelist, etc.

Would be happy to share the code, just lmk!

New comment by spruce_tips in "Claude Opus 4.6"

spruce_tips — Fri, 06 Feb 2026 17:12:07 +0000

Opus is a superior brand line to Sonnet because historically it’s been a more powerful model. I think the thinking behind a rebrand is that people wouldn’t have as willingly switched their usage over from opus 4.5 since that model has been so popular since December 2025.

Calling it part of the Sonnet line would not provide the same level of blind buy in as calling it part of the Opus line does

New comment by spruce_tips in "Claude Opus 4.6"

spruce_tips — Thu, 05 Feb 2026 18:09:34 +0000

Ah yes, explains why it takes 3 seconds for a new chat to load after I click new chat in the macOS app.

New comment by spruce_tips in "The Codex App"

spruce_tips — Tue, 03 Feb 2026 00:36:36 +0000

Tried it, not impressed. Terrible UX and generally just confusing. Didn't really intuitively know where to go and why. The thing that made me most mad was the clunkiness around pulling specific files into the chat input as context. Like wtf, bad, bad, bad!

New comment by spruce_tips in "Will Google Become Our AI-Powered Central Planner?"

spruce_tips — Fri, 16 Jan 2026 16:06:07 +0000

https://read-faster.com/read/SgIcbUqJ

Read at 600+ wpm using rapid serial visual representation (RSVP)

spruce_tips — Fri, 16 Jan 2026 15:52:32 +0000

Article URL: https://read-faster.com

Comments URL: https://news.ycombinator.com/item?id=46647731

Points: 2

# Comments: 0

New comment by spruce_tips in "Eat Real Food"

spruce_tips — Wed, 07 Jan 2026 21:48:27 +0000

wow, it's almost like this makes sense

New comment by spruce_tips in "Graphite is joining Cursor"

spruce_tips — Fri, 19 Dec 2025 18:53:13 +0000

composer 1 has been my most used model the past few months. but i only use it to execute plans that i write with the help of larger, more intelligent models like opus 4.5. composer 1 is great at following plan instructions so after some careful time providing the right context and building a plan, it basically never messes up the implementation. sometimes requires a few small tweaks around the edges but overall a fantastic workflow that's so delightfully fast

New comment by spruce_tips in "GPT-5.2"

spruce_tips — Fri, 12 Dec 2025 00:52:54 +0000

it took me a lot of tinkering to get this feeling seamless in my own apps that use the api under the hood. i ended up buffering every token into a redis stream (with a final db save at the end of streaming) and building a mechanism to let clients reconnect to the stream on demand. no websocket necessary.

works great for kicking off a request and closing tab or navigating away to another page in my app to do something.

i dont understand why model providers dont build this resilient token streaming into all of their APIs. would be a great feature

New comment by spruce_tips in "Anthropic acquires Bun"

spruce_tips — Wed, 03 Dec 2025 00:21:55 +0000

try java 25, and update your priors :)

New comment by spruce_tips in "Building more with GPT-5.1-Codex-Max"

spruce_tips — Mon, 01 Dec 2025 21:26:42 +0000

it's in cursor only

New comment by spruce_tips in "Google, Nvidia, and OpenAI"

spruce_tips — Mon, 01 Dec 2025 21:00:18 +0000

no, i dont think it's a heavier lift to test different model families. my point was that swapping models, whether that's to different model families or to new versions in the same model family, isn't straightforward. i'm reluctant to both upgrade model versions AND to swap model families, and that in itself is a type of stickiness that multiple model providers have.

maybe another way of saying the same thing is that there is still a lot of work to make eval tooling a lot better!

New comment by spruce_tips in "Google, Nvidia, and OpenAI"

spruce_tips — Mon, 01 Dec 2025 19:22:04 +0000

I agree there is no moat to the mechanics of switching models i.e. what openrouter does. But it's not as straightforward as everyone says to switch out the model powering a workflow that's been tuned around said model, whether that tuning was purposeful or accidental. It takes time to re-evaluate that new model works the same or better than old model.

That said, I don't believe oai's models consistently produce the best results.

New comment by spruce_tips in "Building more with GPT-5.1-Codex-Max"

spruce_tips — Thu, 20 Nov 2025 01:35:33 +0000

100% agree. composer-1 really has been the sweet spot for me of capability, reliability, and speed. i dont ask it to do too much at once, and this approach + its speed, materially speeds my work up. i generally find i get the most out of models when i feel like im slightly underutilizing their capabilities. the term i use for this is "staying in the pocket"