krmmalik

Oh how I wish there was an Apple TV app for this. I do all my YouTube browsing on an Apple TV.

I like to use OpenAI models for ingesting a customer brief, usually a paragraph or two and then a read of a several customer files (eg spreadsheets and docs etc) and turning it into a system design blueprint. I'm currently using Astra for this phase but it's incredibly expensive relative to the other tasks that come after this. Would you recommend I stick to Astra or can I downgrade to say Sol or Terra for this job?

I'm just worried the system design won't be as good if I choose a lesser model so to speak.

Edit: typos/grammar

Thanks!

I read the entire manifesto thinking the discourse about a code execution model would lead to a revelation that this is a model that can reduce bugs in code in realtime and make sure the code runs to the original spec or blueprint. Instead it turned out to be about a model that keeps on optimising code that can go faster and faster over time. That's very exciting in its own right, don't get me wrong, but I was really starting to hope this would be about creating code that breaks less etc.

Maybe it means both but perhaps the emphasis is on speed.

I asked DeepSeek believe it or not and it recommended YanChao (formerly Gonest.cn).

I've had an "ok" experience so far. Not amazing, but not horrendous either. I kinda suspect it's just the specific staff member that has been assigned to me, and maybe a different member of personnel might provide a slightly better experience, but as I say, it's not been horrendous or truly awful. Just a little lacking. I generally find the Chinese to be far more eager to please and provide a good service but I think these guys are a little inundated so it's hard to keep up.

I've just ordered a dining table and a set of dining chairs from China using a sourcing agent mixed with TaoBao. It's costing me about £1200 ($1500) so far delivered to the door and if I was to buy this complete setup in the UK, it would cost about £2500. The only problem has been delivery time and the back and forth with the Chinese sourcing agent hasn't been great in terms of communication, but I'll be damned if I'm going to give an extra £1000 to Western retailers that are hellbent on following the Amazon model and ripping off customers.

Exactly, according to these benchmarks Gemini 3.8 Flash is the best option at that budget level for coding, but in real world testing, I found DeepSeek flash to perform far better at a much lower price.

As a non-coder I was obsessed with automation tools like Zapier when they first came out. After that, I tried very hard with n8n but just found it impossible to work with until I read some post by some developer that said "just do it in Python". Took me a while to really take that in given I can't code but then I got Claude to write some Python scripts automate some work spreadsheet and API work and I haven't looked back since.

I think something like this could have worked several years ago but now it's overkill.

My understanding is that Opus should be used for planning, macro-level conversations and Sonnet for execution.

So, for coding, for example: Opus for solution design and architectural blueprint and then Sonnet for actual implementation.

Works out cheaper with minimal loss of quality.

At least that's my personal understanding and anecdotal experience.

I've been wanting something like this for years, ever since we all started to go google as a first port of call and ever since the algorithm changes it's been harder and harder to find out what people are saying about a product without getting hit with corporate/ad spam. I just tried it with a few searches for actual stuff I need more info on and the results were very satisfactory, so well done.

This is a really well thought out product. Well done. You have solved a very real problem with this product in a very fitting way. I also really liked the 3D animation on the kickstarter page. I will buy one as soon as I have some spare cash.

I asked "How can I stop my kidneys being overactive" and got a surprisingly satisfactory result and my question has been answered.

Honestly speaking, I had very low expectations going in so this was a nice surprise.

What about the DAML smart contract language? It's currently being used to digitalise the world's largest stock exchange (Hong Kong) and the Australian Securities exchange