LeicaLatte

I got out of GitHub last year and self hosted a vps that runs gitea.

My work llm provider is GitHub copilot and we are completely blocked since morning. My question is who’s comparable to copilot vscode and cli. Multi model is table stakes.

If china captures the market now, well deserved. Way cheaper compared to us providers.

My setup is very similar.

After you log in you can unlock keychain by running this command

‘security unlock-keychain’

Completion API is only half the product. Teams integrate these tools into production with nothing but policy documents between them & incidents. The guardrail system does not exist for a reason. No business model. No investors. No revenue stream.

Tesla didn't just build FSD. They had to build a verification layer: driver cameras, steering sensors, attention alerts. That parallel software makes autopilot road ready.

Instead of reinventing terminals, what if we standardized on structured data exchange between CLI tools (like JSON/msgpack) and let terminal emulators render it intelligently? The backwards compatibility problem that nixpulvis mentions is real - any "terminal of the future" needs to run existing tools well first while gradually enabling richer experiences.

A simple "END OF ARTICLE" delimiter in prompts might prevent most of these embarrassing slips.

Great timing - launching right as the transformer bubble might be peaking.

YouTube's messaging is the more frustrating part about all this. Panic might drive more creators toward direct monetization, that might just be the better net outcome.

Mobile apps often sort by creation time in the UI (chat messages, activity feeds). Since clients only see the masked version, there might be a need to expose a separate timestamp field.

I think the 73% non-work usage ratio will flip again within 2-3 years, but not because consumer usage shrinks. As AI becomes embedded in workflows through APIs the "work" category is set to expand dramatically.

Curious about the interaction between this memory behavior and fine-tuning. If the base model has these emergent memory patterns, how do they transfer or adapt when we fine-tune for specific domains?

Has anyone experimented with deliberately structuring prompts to take advantage of these memory patterns?

Liking the package management from first principles as a systems-level optimization problem rather than file scripting. resembling a database engine - dependency aware task scheduling, cache locality, sys call overhead - they are all there.

Very cool. I would probably build this using SDUI server driven abstractions. Curious if you considered that approach to build bitrig or parts of it.

I just hate arrays.

Loving all these Claude Code as a Platform products. Hope Anthropic doesn't ban them once they become popular citing some vague TOS violation.

bookmarking is such a lightweight task (like vpn), compute and storage wise, there is no reason to not self host it. many nice solutions out there, i personally use wallabag. its gets many things right.

This isn’t the Apple I remember. Product integration falls apart at every seam, but don’t worry—we’ve got plenty of impressive technical documentation to compensate. I’m sure Jobs would be thrilled to see his ‘it just works’ philosophy replaced with ‘it barely works, but here’s a 50-page PDF explaining why.

The video replay thing was the only cool thing in that demo.

Customers are always chasing the next big thing in this space. As a programmer who’s worked on mobile UIs and backends using CC, I can say the appeal isn’t really the model itself—it’s the form factor. It’s a decent product, but hardly groundbreaking or essential.

Do things that don’t scale taken to another level :)

Add that external payment button and watch my app magically disappear from search results.

Sure, they changed the rules on paper, but who's policing their algorithm? Nobody. They can tank my keywords overnight and call it "normal fluctuation."

FAANG will be fine, but indies? Gentle reminder that ASO funnels have no customer support. Might just suddenly "stop working."

Anyone else afraid to pull the trigger on this?

i've recently set claude 3.7 as the default option for customers when they start new chats in my app. this was a recent change, and i'm feeling good about it. supporting multiple providers can be a nightmare for customer service, especially when it comes to billing and handling response quality queries. with so many choices from just one provider, it simplifies things significantly. curious about how openai manages customer service internally.

I would love to move away from railway to Coolify or dokploy. Someday.

Google leadership has had a measured approach and product releases seem more baked than ever, it’s refreshing to see. Their 0 to 1s feel compelling and more Apple(2000s) like.

Might be a fun exercise to write a serialuzation/deserialization library using these features.

More pot stirrer than ai overlord kind of move by Musk here.

Awesome project! Direct sensor connectivity is an interesting approach. Skipping the phone app is a big win.

Every reasoning inquiry should start with this Reasoning 101 question. R1 got it right -

https://chatlabsai.com/open-chat?shareid=MbSUx-vUDo

How many words are there in your response to this prompt?

There are 7 words in this response.

Promising start.

For comparison here is the 4o response - https://chatlabsai.com/open-chat?shareid=PPH0gHdCjo

There are 56 words in my response to this prompt.

I had no idea. Only highlights how much I have read their docs or marketing.

We are a family of three and the 25 institution limit seems fine to us.

No affiliation. Never read their marketing.