1
point
spruce_tips
Joined 85 karma
- spruce_tipscomposer 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
- try java 25, and update your priors :)
- it's in cursor only
- 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!
- 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.
- 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"
- 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
- lol
- 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
- 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
- checkout java 23. it has come a long way
- 1 point
- 1 point
- honest question - why dont companies just hire software engineers under the guise of some other title like "researcher"? would that allow them to get around the 5 year depreciation? how is it even enforced?
- interesting, but not surprising
- doesnt mean the video isnt ai generated
- i thought so too. way too weird looking. there's a reason they zoomed on their faces whenever they were talking - to hide the unnatural hand movement