mattfrommars

I need to understand how do you guys build such slick or decent UI for websites. I get the backend but the front end, I have yet to crack. I know there is impeccable repo but I'm unsure how to go from here

This is incredible stuff OP Why is this being flagged?

This is literally what CodeCradt did!

Which LLM model actually built this? I looks very sloppy.

I have same the same FOMO to use SOTA model for all planning and brainstorming session. However, I’m unsure how do you bring deepseek for subagent task. Could you describe your workflow?

For myself, using Codex, I always have to explicitly tell codex to use Luna with high reasoning for smaller, bit size tasks.

I asked Claude how will ETH being solved is a major breakthrough for mankind:

“ Honestly, nothing yet. This is a theoretical result, and it doesn't solve a real-world problem today.

*Why it won't change much in practice:* A running time like 2^(n/√log n) is "subexponential" on paper, but for real inputs it's still astronomically slow. For a few hundred variables it's no better than the brute-force methods we already have. Hidden constants in the exponent could also make it worse in practice. Real-world SAT solvers (the CDCL kind) already handle millions of variables on practical problems using heuristics, and this result doesn't replace them.

*Where SAT shows up in everyday life, indirectly:* - Verifying that chips (like the one in your phone) have no design bugs - Scheduling and logistics, like timetables, delivery routes, and airline crews - Software package dependency resolution - Security analysis and cryptography research

*What it could change over time:* - *Research direction:* Many problems were assumed to be hard because ETH says so. If ETH is false, researchers may find faster algorithms for them, and some of those could eventually matter in practice. - *Cryptography:* It doesn't break encryption, since the algorithm is still far too slow. But it could shift how people think about the hardness assumptions behind some security arguments. - *Theory of math and proof:* The Lean verification is also a notable example of AI-assisted, machine-checked mathematics.

So the "big deal" is mainly for computer scientists: a long-held belief about the limits of computation may be wrong. Any benefit to normal people would be long-term and indirect, and only if it leads to practical algorithms.“

Do people use deepseek for real world development or just for building experimental large projects?

My understanding is API prices are more expensive then monthly plan, is this true?

My plan for OpenAI recently expired and now I’m thinking to test Anthropic ecosystem. My primary use case is programming only.

Should I go with API use or subscription? For coding harness, I jump between codex, OpenRouter, pi, whatever coding harness is trending on that day

How did you ensure code generated by LLM did not com from Linux source code?

I'm actually in update NY. I've only been reached out from HarveyAI recently. But that's about it.

I’ve been wanting to get into legal tech but I never managed to find the opportunity to get in or found folks who are interested in this space. Now I wonder if it’d bit too late to get into this space since now they are startups valued in billions

This is amazing. I can’t wait benchmark to come out $ per performance

I repurposed my old macbook pro from 2013 as dedicated Proxmox machine. I run all short of application on it - mostly pulled from https://community-scripts.org/. Along this, I use free tier of Oracle VM to funnel traffic to my box and use that as reverse proxy appliance. Thee isn't a real need to pay $5-$10 for a VPS if you have old machine lying around and use AI to help you configure it. I gave my setup using whichever LLM model I want to use at that day full access via SSH keys.

Congrats to the OpenRouter team.

I vividly remember back in 2023/2024, I was sitting on my sofa thinking, "there has to be a market to abstract data access layer, something like Terraform but for LLM provider to avoid vendor lockin". Only if I had access to capital to build something like that at that time, I could have been my try for an AI start up.

Sorry, I can't really help you with the tool as I don't have access to it in my day to day job, but are you really the creator behind https://github.com/Tura-AI/tura I which I assume is solo dev project?

> The bigger issue is that console manufacturer revenue is highly cyclical. This is hard to see in e.g. Xbox and Sony since they are both part of a larger conglomerate, but really obvious for nintendo.

There is absolutely no reason to be in sync with Sony on their console release date. They could have effectively released consoles bit more frequently. But they choose not to do so. Their acquisition has been questionable - Activision/Blizzard.

At the end of the day, the employee pay the price for bad management decision which they keep on making.

Anyone know what will lawfirms cut if they win from the lawsuit?

How many millions are we talking.

I feel Boston Dynamics appears to be doing far more impressive work to be way 'cheaper' then how much Cursor (60b) or Wiz was acquired for (32b)

This is incredible. Amazing job Anthropic!

Now when will the innovation happen where say cost of running Haiku performs level of Opus 4.5?

I feel models are only getting bigger instead of models becoming more efficient and cheaper to run

That sounds about right. People generally under estimate how old Ancient Egyptian really are, me included and think it sometimes around the era of Middle Ages.

Incredible and congrats. I'm doing a bit retro that during the boom of AI and LLM, I was busy doing my day job in Java CRUD and figuring things out about micro services.

It had never occurred to me to go like, "I'm going to make an open source product for LLM". How is something like built from scratch from an idea? And what is the idea?

For example, it is fairly straight foreword to build a dash board of something with React as front end + backend API. This will be a typical web app.

But stainless is something different, from my limited knowledge in this space, its appears to be SDK, something like OpenAI SDK that reduces boilerplate code to interact with LLM providers by providing list of tools (MCP), temperature, context memory and bunch of other parameters...

Depends worker from which demographic. Worker from India is far cheaper then worker who is in California.

I have lot and hate relationship with windows native desktop application. As a kid, I use to look for something GUI application and .exe application since they are breeze to run and just felt right. Now in my day job, I just dislike developing for windows desktop application - partly probably the application is massive and super slow to develop or just there isn't a lot of investment from the company stand point into the product.

This got vibed coded AF

Yah but browser and computing are so much powerful, who needs to install software on their machine when web app and apps store is sufficient for general consumers

As someone who has been in the line of PC building, the entire “build your own” industry has been in a decline. And this “RAM apocalypse” is pretty much nail on the coffin.

Enterprise business from small, medium to large get laptops or use mobile application and online SAAS.

There entire PC industry is for enthusiasts and tiny segment of the worlds computing needs. The laptop variation has already been eating into PC market.

In today’s world, it’s just not practical to own a PC unless you are gamer. And for gamers, it’s just better to get console. And for developers, their is more money to be made selling games on console then PC.

In the end, from business, to revenue generation stand point, custom PC industry is just a legacy of old computing world. As I type this, custom PC is more of a “marketing segment” for Nvidia for example to upsell Nvidia cloud offering - i might be stretching too far - but that basically is the point.

Yeah, I’ve come to the same realization. Israel does the dirty work for the US and they take all the heat. If the U.S. really wanted Israel to stop, all they need to do is take out special privileges Israel gets and put down economic sanctions.

That’s good! We need to protect our children.

But who gets the $375 million dollars? Anyone know the cut the law firm will get from this incredible amount of money?

Hmm all my experience with using AI has been mostly VRAM. I haven't experienced any bottleneck on the CPU side. What does this chip offer over Intel or Apple Silicon? Anyone expert here know whatit is?

Agreed. This year around is the best time for OpenAI related firm to IPO. The stock market has been resilient reaching and hovering around ATH. Along with them, SpaceX plans to IPO and will force index fund to purchase their shares at trillion dollar evaluation.

OpenAI and SpaceX firms need exit liquidity - and markets are ready!

My advise for retails folks is to stay invested in the market since these trillion dollar companies cannot afford market to tank at all.

Incredible. I'm more amazed at OP's ability to generate that kind of revenue from SAAS when we live in LLM world where the issue really isn't producing apps, but distribution and turning it into profitability.