Ron

I'm beyond excited to announce Try That LLM: a service for people using LLMs via API. Bulk-test your project's prompts against dozens of LLMs, automatically test them against every new LLM as it ships, and set up LLM judges to score the outputs. Try That LLM is designed for scenarios like these: "Our product uses 20 or so basic prompts...but wow those LLMs are pricey. If we switched some prompts to a cheaper LLM, would quality suffer?" "How do I test my prompts against every new LLM that appears? I don't want to be copy & pasting every time something new ships." "My manager wants to know if we should use LLM XYZ, they read about it on Hacker News. I guess I'm spending my day figuring that out." "I just want something to score the responses and tell me the best one" "Which prompts are costing us the most?" If you get a chance to try it out, I'd love your feedback/comments. trythatllm.com

@maxescu These are great! Do you find you have to iterate on your prompts much? i.e. you have a vision for the eventual chart, and it only takes one or two prompt iterations to get it right? Or does it take many iterations, tweaking as you go?

I’m obsessed with creating charts with the new ChatGPT Image-2. Maybe because I spent years doing these manually in Illustrator, Sketch, or Figma. And to be honest, I enjoy prompting design systems, and then inputting the data. It feels logical. Examples and prompts:

@lkr It seems like "regency bias" should indeed already be a thing: it's whatever the King & Queen like...

Definitely read this as regency bias and was intrigued by this new kind of bias I had not heard of

@AIWarper Did the video get cut off? It's only 48 seconds for me. So I assume the prompt to Gemini included basically "use this output format" with an example, and Gemini filled in all the shot start/stop times, with shot notes? Cool!

💫Anime intro created in 1hr with Seedance 2 Full explanation of how I did this in the comments below. If this interests you please consider engaging 💙

@maxescu Super cool, thanks for posting this, with real-world math. I don't know if you've tried LTX 2.3 for dialogue yet, but the performances are shockingly good. Intersperse some character/performance notes in between every sentence of quoted dialogue, and the results are top-notch.

$30,000 used to be the minimum for a music video. 20-35 crew members. Multiple shooting days. Weeks of post. This took me 8 hours at home using the LTX 2.3 open-source framework. Watch first, then read the full breakdown below:

@AIWarper Eleven Labs is shockingly good. You might enjoy the streaming version of their TTS API...

What is the best “realtime” text-2-speech solution today? Paid or free but it needs to be near real time. Admittedly an area I haven’t kept up with but now need it for something 🥲

@maxescu @invideoOfficial Wavespeed and Fal let you toggle web search on/off too. They don't have a friendly workflow UX, but if you're using like n8n you should be in business.

I was testing a prompt I originally ran in @invideoOfficial, but after trying it in Higgsfield, Freepik, Krea, and others, nothing was working properly. I tried to correct the prompt multiple times, as I thought I was doing something wrong. But then it hit me: invideo is the only one with Web Search enabled for Nano Banana 2, allowing it to parse results in real-time or from given links, and conduct research before generating the image. On the other platforms, I was getting random games instead of the one I specified in the prompt, which tells me it was ignoring my link. I feel like this is something everyone else missed out, except invideo, which implemented Nano Banana 2 in a very smart way. Kudos to them! Check out the results from a few platforms, and the prompt below:

@eyishazyer This looks amazing--what tool is it from?

This Real Time Data in Motion is WILD‼️

@fofrAI Those drink cans look amazing!

> A scan of a print from a found roll of film, the film had been lost for years. Not a negative. No datestamp or written text. It's just been printed for the first time, so the print is pristine.

Do you hand-edit/compose your json? I tried converting that json to toon format (which uses spaces), and got basically identical images...feels a little more readable...fwiw! --- meta: quality: ultra photorealistic resolution: 8k camera: iPhone 15 Pro lens: 24mm wide aspect_ratio: "9:16" style: "raw iPhone photo, natural apartment lighting, zero post-processing, authentic GRWM" character_lock: age: mid-late 20s (clearly adult) ethnicity: Mediterranean / Middle Eastern / Southern European (olive skin tone) hair: color: "dark brown, almost black" style: "sleek pulled-back low bun, center part, very smooth and polished" eyes: "dark brown, almond-shaped, striking" face: shape: oval with refined features cheekbones: high and defined jawline: sharp and elegant skin: "smooth olive complexion, natural texture" accessories: glasses: "oversized tortoiseshell frames, intellectual chic style" body: type: "slim athletic, tall model proportions" legs: "long and lean, fully visible" scene: location: modern high-rise apartment living room time: golden hour / late afternoon atmosphere: "bright, airy, natural luxury" camera_perspective: pov: "iPhone on tripod, self-timer shot" camera_mode: standard back camera - NO portrait mode distance: 3-4 meters back to capture FULL BODY head to toe including feet angle: straight-on at chest/waist level framing: "vertical 9:16, full body centered from head to floor, NO CROPPING OF LEGS OR FEET" focus: everything sharp - her AND entire apartment background clear floor_visible: bottom of frame shows floor beneath her feet subject: action: posing confidently for GRWM outfit photo pose: position: "standing center of living room, floor-to-ceiling windows behind" stance: "confident - weight on one leg, hip popped, feet visible" legs: "full legs visible from hips to feet, natural stance" hand_on_hip: "one hand placed on hip/waist, elbow out" other_arm: relaxed at side or adjusting cardigan posture: "tall, shoulders back, elegant" head: tilt: straight or very slight tilt gaze: direct confident eye contact with camera expression: "soft natural smile, comfortable and confident" outfit: cardigan: type: oversized knit cardigan color: forest green / emerald green fit: "slouchy, worn open" length: "hip length, ends at top of shorts" sleeves: "long, slightly pushed up or hanging natural" texture: chunky ribbed knit visible top: type: silk or satin camisole color: cream/ivory white neckline: V-neck fit: "fitted, tucked into shorts" straps: thin delicate straps barely visible under cardigan shorts: type: high-waisted tailored linen shorts color: cream/beige/natural linen fit: "relaxed tailored, pleated front" length: mid-thigh waist: sits at natural waist details: "clean lines, quality linen texture" belt: type: wide leather belt color: tan/cognac brown leather buckle: square or rectangular metal buckle placement: cinched at waist over shorts shoes: type: heeled ankle boots color: brown/cognac leather style: "pointed or rounded toe, stacked heel" height: ankle height VISIBILITY: FULLY VISIBLE - both boots in frame accessories[3]: large tortoiseshell eyeglasses,small gold hoop earrings,delicate gold necklace (optional) hair_makeup: hair: "sleek low bun, pulled back tight, center part, polished" makeup: "natural fresh - glowing skin, neutral tones, nude lip" environment: living_room_layout[5]: floor-to-ceiling windows behind her showing SHARP city view,modern high-rise apartment (15-25 floors up),"buildings and sky clearly visible outside, NO BLUR",light neutral walls (white/cream),light wood or gray flooring fully visible furniture_left_side[3]: modern sectional sofa in neutral tone (beige/taupe),"textured throw pillows (olive green, cream tones)",sofa faces camera angle furniture_center[3]: large rectangular marble coffee table with terrazzo/speckled pattern,styled with coffee table books stacked,decorative objects on table furniture_right_side[3]: modern console table or media unit,light wood finish,minimal styling on top flooring[2]: light wood planks or neutral tile,area rug under coffee table (neutral textured) lighting: type: natural window light flooding entire space time: golden hour warm afternoon effect: "soft backlight from windows, warm glow on everything" shadows: natural soft shadows on floor city_view: clarity: 100% sharp and detailed visible: "apartment buildings, sky, urban landscape all clear" vibe: mood: "effortless chic, apartment lifestyle content" energy: "confident creator, showing off styled outfit" content: classic GRWM full outfit post photography_rules: critical_framing: full_body_requirement: MUST show complete body from head to feet feet_visibility: both feet and shoes fully visible in frame floor_space: show floor beneath and around feet no_cropping: "do NOT crop legs, ankles, or feet" headroom: small amount of space above head camera_distance: far enough back to capture everything camera_specs: mode: standard iPhone photo - NOT portrait mode focus: everything sharp - no background blur depth: natural perspective only exposure: balanced for room with backlight from windows authenticity: no_artificial_blur: true no_bokeh: true background_sharp: true natural_iPhone_capture: true zero_post_processing: true realism: skin: "natural texture, real pores" lighting: true natural light behavior colors: iPhone natural warm tones sharpness: crisp but natural

finally got the formula for my ai influencers { "meta": { "quality": "ultra photorealistic", "resolution": "8k", "camera": "iPhone 15 Pro", "lens": "24mm wide", "aspect_ratio": "9:16", "style": "raw iPhone photo, natural apartment lighting, zero post-processing, authentic GRWM" }, "character_lock": { "age": "mid-late 20s (clearly adult)", "ethnicity": "Mediterranean / Middle Eastern / Southern European (olive skin tone)", "hair": { "color": "dark brown, almost black", "style": "sleek pulled-back low bun, center part, very smooth and polished" }, "eyes": "dark brown, almond-shaped, striking", "face": { "shape": "oval with refined features", "cheekbones": "high and defined", "jawline": "sharp and elegant", "skin": "smooth olive complexion, natural texture" }, "accessories": { "glasses": "oversized tortoiseshell frames, intellectual chic style" }, "body": { "type": "slim athletic, tall model proportions", "legs": "long and lean, fully visible" } }, "scene": { "location": "modern high-rise apartment living room", "time": "golden hour / late afternoon", "atmosphere": "bright, airy, natural luxury" }, "camera_perspective": { "pov": "iPhone on tripod, self-timer shot", "camera_mode": "standard back camera - NO portrait mode", "distance": "3-4 meters back to capture FULL BODY head to toe including feet", "angle": "straight-on at chest/waist level", "framing": "vertical 9:16, full body centered from head to floor, NO CROPPING OF LEGS OR FEET", "focus": "everything sharp - her AND entire apartment background clear", "floor_visible": "bottom of frame shows floor beneath her feet" }, "subject": { "action": "posing confidently for GRWM outfit photo", "pose": { "position": "standing center of living room, floor-to-ceiling windows behind", "stance": "confident - weight on one leg, hip popped, feet visible", "legs": "full legs visible from hips to feet, natural stance", "hand_on_hip": "one hand placed on hip/waist, elbow out", "other_arm": "relaxed at side or adjusting cardigan", "posture": "tall, shoulders back, elegant", "head": { "tilt": "straight or very slight tilt", "gaze": "direct confident eye contact with camera" }, "expression": "soft natural smile, comfortable and confident" }, "outfit": { "cardigan": { "type": "oversized knit cardigan", "color": "forest green / emerald green", "fit": "slouchy, worn open", "length": "hip length, ends at top of shorts", "sleeves": "long, slightly pushed up or hanging natural", "texture": "chunky ribbed knit visible" }, "top": { "type": "silk or satin camisole", "color": "cream/ivory white", "neckline": "V-neck", "fit": "fitted, tucked into shorts", "straps": "thin delicate straps barely visible under cardigan" }, "shorts": { "type": "high-waisted tailored linen shorts", "color": "cream/beige/natural linen", "fit": "relaxed tailored, pleated front", "length": "mid-thigh", "waist": "sits at natural waist", "details": "clean lines, quality linen texture" }, "belt": { "type": "wide leather belt", "color": "tan/cognac brown leather", "buckle": "square or rectangular metal buckle", "placement": "cinched at waist over shorts" }, "shoes": { "type": "heeled ankle boots", "color": "brown/cognac leather", "style": "pointed or rounded toe, stacked heel", "height": "ankle height", "VISIBILITY": "FULLY VISIBLE - both boots in frame" }, "accessories": [ "large tortoiseshell eyeglasses", "small gold hoop earrings", "delicate gold necklace (optional)" ] }, "hair_makeup": { "hair": "sleek low bun, pulled back tight, center part, polished", "makeup": "natural fresh - glowing skin, neutral tones, nude lip" } }, "environment": { "living_room_layout": [ "floor-to-ceiling windows behind her showing SHARP city view", "modern high-rise apartment (15-25 floors up)", "buildings and sky clearly visible outside, NO BLUR", "light neutral walls (white/cream)", "light wood or gray flooring fully visible" ], "furniture_left_side": [ "modern sectional sofa in neutral tone (beige/taupe)", "textured throw pillows (olive green, cream tones)", "sofa faces camera angle" ], "furniture_center": [ "large rectangular marble coffee table with terrazzo/speckled pattern", "styled with coffee table books stacked", "decorative objects on table" ], "furniture_right_side": [ "modern console table or media unit", "light wood finish", "minimal styling on top" ], "flooring": [ "light wood planks or neutral tile", "area rug under coffee table (neutral textured)" ], "lighting": { "type": "natural window light flooding entire space", "time": "golden hour warm afternoon", "effect": "soft backlight from windows, warm glow on everything", "shadows": "natural soft shadows on floor" }, "city_view": { "clarity": "100% sharp and detailed", "visible": "apartment buildings, sky, urban landscape all clear" } }, "vibe": { "mood": "effortless chic, apartment lifestyle content", "energy": "confident creator, showing off styled outfit", "content": "classic GRWM full outfit post" }, "photography_rules": { "critical_framing": { "full_body_requirement": "MUST show complete body from head to feet", "feet_visibility": "both feet and shoes fully visible in frame", "floor_space": "show floor beneath and around feet", "no_cropping": "do NOT crop legs, ankles, or feet", "headroom": "small amount of space above head", "camera_distance": "far enough back to capture everything" }, "camera_specs": { "mode": "standard iPhone photo - NOT portrait mode", "focus": "everything sharp - no background blur", "depth": "natural perspective only", "exposure": "balanced for room with backlight from windows" }, "authenticity": { "no_artificial_blur": true, "no_bokeh": true, "background_sharp": true, "natural_iPhone_capture": true, "zero_post_processing": true }, "realism": { "skin": "natural texture, real pores", "lighting": "true natural light behavior", "colors": "iPhone natural warm tones", "sharpness": "crisp but natural" } } }

A deeper dive: trythatllm.com/blog/Ukrainian…

After trying a few approaches for translating text from Ukrainian with 10 LLMs: "Translate this into English" vs. "What does this phrase mean": Asking for the meaning generated more thorough responses than just asking for the translation. "Without preamble, commentary, or quotation marks, translate this into English": On the other end of the spectrum, this worked to get just the translated text itself, without the LLM's commentary

All the prompts and responses in a table on Try That LLM: trythatllm.com/public/pg/9Jji…

Feb. 24 makes it four years since Ukraine was invaded by Russia. I thought I'd test out 10 LLMs and see how they did with Ukraine-related topics and translations. Ukrainian is spoken by 30-40 million people, around eighth-most in Europe, so it's an interesting test. I had a native Ukraine speaker friend look at most of the outputs to weigh in on their accuracy. I'll post snippets here over the next few days; if you'd like the full breakdown and the actual prompts + responses, links are in the comments.

A post diving into more detail: trythatllm.com/blog/Ukrainian…

@AIWarper There are some creators who are great at highlighting open source/weights stuff: @pixaroma" target="_blank" rel="nofollow noopener">youtube.com/@pixaroma @BenjisAIPlayground" target="_blank" rel="nofollow noopener">youtube.com/@BenjisAIPlayg… (AI voice is terrible, but content is decent) @mickmumpitz

Is there anything worth playing with in open source right now? LTX was promising but honestly I have zero motivation to dive into that at this point.

@iannuttall Molmo is made for this, try allenai.org/molmo . Open weights, can run it on their playground, or on Wavespeed for ~6 cents per footage-minute. Qwen has a set of VL models too, but you might need to do your own frame extraction.

Has anybody figured out how to give a video to AI and have it look at the scenes to summarise what the video shows, where transitions are, etc?

@d4m1n Nice tip, thank you sir. And thank you for including the prompt! FWIW, if the window is narrow, the left-right text-image alignment causes the text to be overwritten. But I think you don't care, because you basically made a mini-site just to generate the movie, right?

this is why AI is so disruptive. 3y ago I paid $2000 for an animation for clobbr.app. it took 4 weeks. today I paid $25, it took 15min 🤯 would you still pay 80x the price for the professional work?

@yayalexisgay @TessTregellas Nice camera work! (also nice writing and performances)

@kleneway I'm curious to hear about how this turns out--I wonder if ~5s screenshots would be enough to get the context of what a user is trying to do...

Weekend project - cron job to screenshot my laptop every five seconds, then use a codex automation to take notes and eventually create skills for my repetitive tasks.

@d4m1n Also add "Make no mistakes!!!1!"

guy almost hacked my vibe coded OS how to avoid: add "remember to implement security" at the end of each prompt