Richard Roxas
@chard_sourcex
Followers
186
Following
181
Media
14
Statuses
261
Technical Support @lmsqueezy Indie hacker & solopreneur. Full stack dev | React. 6+ years IT & customer service. Solving specific problems using AI!
Joined January 2011
Shipped @OpenAI New Image generation API first thing in the morning. Also worried about usage cost so I added estimation cost for high, med and low quality. TLDR: High: 1 image $0.17 Medium: $0.04 Low: $0.01 #buildinpublic
2
1
7
They really shipped! Time to add more models to our Advance Voice mode!
2
0
0
also codex is now in the api time to cook 🔥🔥🔥
GPT-5-Codex is live in the Responses API. If you use the Codex CLI via API key, you can now also use GPT-5-Codex.
7
3
84
Cursor 1.0 is out now! Cursor can now review your code, remember its mistakes, and work on dozens of tasks in the background.
439
1K
12K
Let's try this beast!
Sonnet 4 is available in Cursor! We've been very impressed by its coding ability. It is much easier to control than 3.7 and is excellent at understanding codebases. It appears to be a new state of the art.
0
0
1
Woah , it can sing!
0
0
0
Imagen 4 and Veo 3 (with native audio), our SOTA image and video models, are rolling out right now and will be available to start in the @GeminiApp API soon : )
124
72
2K
Sheesh! A must try API , native audio generation
Say goodbye to the silent era of video generation: Introducing Veo 3 — with native audio generation. 🗣️ Quality is up from Veo 2, and now you can add dialogue between characters, sound effects and background noise. Veo 3 is available now in the @GeminiApp for Google AI Ultra
0
0
1
Cursor now supports 1M context-windows, the most expensive models, and unlimited tool calls with API pricing.
How do you think we should be pricing for very expensive models (o3) or ultra-long context windows (~100k LOC) in Cursor? API pricing, higher subscription tier, something else?
71
71
2K
What a great deal @elevenlabsio Time to build on 11labs agent again..
Today ElevenLabs is launching AI Engineer Pack volume four. With deals from @modal_labs, @MistralAI, @NotionHQ, @browser_use, @intercom, @huggingface, @coderabbitai and many more, it has everything you need to get started building an AI startup. We can't wait to see what
0
0
0
Building one
What’s the simplest way for me to integrate tons of MCP servers quickly into a chatbot, and allow users to access them?
0
0
0
Exactly my thought!
I have worked with pretty much every major AI model/provider. They all have strengths, but man do they have some weird issues too. I've been keeping a list. Decided to share because why not? Here's everything I hate about Gemini, Claude, ChatGPT and Mistral.
0
0
0
2006, tryna code C++ with nothing but paper, flowcharts, and a 1-hour lab slot per week. Library books? Barely helpful. Kids today got AI answering every question. So jealous, but man, that grind was real.
Im so envious of people who learn to code today. Be me learning to code in 2018, having to either browse page 10 of Google to find an obscure Stack Overflow page. Or be lucky to have coder friends you can ask 20 thousands questions a day. Kids these days have a
0
0
0
goodbye, GPT-4. you kicked off a revolution. we will proudly keep your weights on a special hard drive to give to some historians in the future.
2K
2K
44K
ChatGPT-4o image gen is insane. People can't stop finding new creative ways to use it. 10 wild examples + prompts & how to:
72
274
2K
Fun little experiment with ChatGPT 4o! Prompt: Draw an action figure toy of the person in this photo. The action figure should be full-figure and displayed in its original blister pack packaging. On top of the box is the name of the toy “JERROD” across a single line of text. In
30
47
542
Shipped @OpenAI New Image generation API first thing in the morning. Also worried about usage cost so I added estimation cost for high, med and low quality. TLDR: High: 1 image $0.17 Medium: $0.04 Low: $0.01 #buildinpublic
2
1
7
Damn! Pricing is great!
Image gen is now available in the API! We’re launching gpt-image-1, making ChatGPT’s powerful image generation capabilities available to developers worldwide starting today. ✅ More accurate, high fidelity images 🎨 Diverse visual styles ✏️ Precise image editing 🌎 Rich world
0
0
0
Just added new LLM models from @OpenAI and @Google after a long break. It's satisfying to ship even with 8-5 and lot of errands to do. Continue shipping! #BuildinPublic
1
1
3