spruce_tips
Re:On the Navier–Stokes Millennium Prize Problem
on Tuesday September 08, 2026 @04:17PM (#49616403)
what counts as discounted rate plans? if i pay for a year in advance (and get the yearly discount) and have train on my data set to off.. are you saying that is still being trained on?
Re:MIT Technology Review has confirmed that posts on Moltbook were fake
on Tuesday February 10, 2026 @09:59AM (#46960540)
Yea I knew embeddings I just didn’t quite understand it in OPs context. Makes sense, thanks
Re:MIT Technology Review has confirmed that posts on Moltbook were fake
on Tuesday February 10, 2026 @08:05AM (#46959191)
sorry - what do you mean by embeddings in your last sentence?
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!
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!
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!
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
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!
Re:Claude Opus 4.6
on Friday February 06, 2026 @12:12PM (#46915432)
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
Re:Claude Opus 4.6
on Thursday February 05, 2026 @01:09PM (#46902666)
Ah yes, explains why it takes 3 seconds for a new chat to load after I click new chat in the macOS app.
Re:The Codex App
on Monday February 02, 2026 @07:36PM (#46864578)
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!
Re:Will Google Become Our AI-Powered Central Planner?
on Friday January 16, 2026 @11:06AM (#46647952)
Re:Eat Real Food
on Wednesday January 07, 2026 @04:48PM (#46533474)
wow, it's almost like this makes sense
Re:Cursor Acquires Graphite
on Friday December 19, 2025 @01:53PM (#46329449)
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
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
Re:Anthropic acquires Bun
on Tuesday December 02, 2025 @07:21PM (#46128779)
try java 25, and update your priors :)
Re:Building more with GPT-5.1-Codex-Max
on Monday December 01, 2025 @04:26PM (#46113461)
it's in cursor only
Re:Google, Nvidia, and OpenAI – Stratechery by Ben Thompson
on Monday December 01, 2025 @04:00PM (#46113153)
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!
Re:Google, Nvidia, and OpenAI – Stratechery by Ben Thompson
on Monday December 01, 2025 @02:22PM (#46111806)
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.
Re:Building more with GPT-5.1-Codex-Max
on Wednesday November 19, 2025 @08:35PM (#45987720)
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"
Ask HN: Is anyone using Devin/Cognition?
I've tried it, and wasn't really impressed. Curious if and how teams/individuals here are actually using it, and why!
Re:MIT Study Finds AI Use Reprograms the Brain, Leading to Cognitive D...
on Wednesday September 03, 2025 @04:54PM (#45120307)
yes, in a software engineering context, always use ask mode instead of agent mode unless youre truly doing dumb, tedious work that youve done many times before
Wonder if deprecating direct access means the gpt5 can still route to those behind the scenes?
These presenters all give off such a “sterile” vibe
Re:Ask HN: What are you working on? (July 2025)
on Monday July 28, 2025 @09:49AM (#44710867)
Building low cost tools to give email owner's their attention back.
1. Inbox Toll - solves the "real human, still spam" problem by making the sender pay a fee before the email actually lands in your inbox. Set your toll as low as $0.01.
2. Auto Label - automatically label (+ optionally archive) all non-human messages into logical categories like newsletters, receipts, promotions, etc.
3. Inbox Cleaner - time-based inbox scan that bulk deletes non-essential emails.
---
junkmailcleaner.com
Re:Asyncio: A library with too many sharp corners
on Saturday July 26, 2025 @09:31PM (#44698193)
checkout java 23. it has come a long way
Ask HN: Persisting LLM token streams through a page refresh?
Like many of you, I'm streaming responses token by token from LLMs using server sent events (SSEs). What's the best way to maintain the SSE connection through a page refresh?I haven't seen a lot of documentation or examples covering this. In most LLM enabled apps I've used, if tokens are currently streaming and the page refreshes/changes, the stream gets interrupted.One idea I had was writing...
Ask HN: Persisting LLM token streams through a page refresh?
Like many of you, I'm streaming responses token by token from LLMs using server sent events (SSEs).What's the best way to maintain the SSE connection through a page refresh?I haven't seen a lot of documentation or examples covering this. In most LLM enabled apps I've used, if tokens are currently streaming and the page refreshes/changes, the stream gets interrupted.One idea I had was writing...