GPT 5.6 Luna Max vs 5.6 Sol Medium… Yeah,... it’s not even a question 😭 Sol on MEDIUM produced a much better result than Luna on MAX—and needed only around HALF the time. Same harness. Better generation. Faster result. Luna may be cheaper, but if you have the budget, I would absolutely use Sol. Saving money is not worth it when the weaker output creates hours of extra work later.show more

personalized shopping with Astra is unbelievable I did something... similar with GPT-5.6-Sol (not on ultrafast) and while Sol got the job done, Astra did a way better job on reproducing my like (face + body) and was ~4x faster (1 hr 33 min versus 4 hr 24 min)show more

Grok 4.5 performed GPT Sol level for free! We... gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.show more

I tested Qwen 3.8 Max vs Kimi K3 Same... scene, lighting, props, detail requirements. Qwen's output is decent, but it's not close to Kimi K3. Qwen's output came out messy, text handling was off, and the composition felt unorganized next to Kimi's version. In my opinion, Qwen isn't second to Fable 5 either, and it's also below GPT-5.6 Sol. It's a solid model, but not at that tier. Kimi K3 is still clearly ahead here.show more

It's never been a better time to be creative.... (ever) The two best frontier models (ever) have been released within 30 days of each other. Here’s what we learned from running 4 frontier models head to head. >Sol has taste and Fable takes direction. 10 identical landing page briefs, judged blind by working creatives. GPT 5.6 Sol won 82% on loose briefs. But when handed a real design spec it finished last. 🧵show more

Holy moly: GLM-5.3 got much better in cybersecurity since... our pre-release evaluation with Z.ai. It now matches GPT-5.6-Sol on our cybersecurity benchmark at 0.4x the cost 🤯 - At pass@1: it went from 60.4% to 65.6% CVEs rediscovered, crushing every other open model on one-shot tasks - At pass@3: it did 75% -> 78.1%, matching GPT-5.6-Sol - Its precision remained stable, reporting fewer false positives than DeepSeek models The performance increase comes from a behavioral change: the new version is more persistent. It tends to run longer, and had a ~43% reasoning tokens increase. But the performance upgrade is worth that additional cost. 1/3 🧵show more

Fusion is the most efficient frontier harness for GPT... 6 Astra and Claude Fable 5.1. You can also configure everything about it: • Base model: Fable, Astra, Sol, or Opus • Sidekick model: SWE (Free), Luna, Sol, GLM (Free) • Speed: Normal or Fast ⚡ • Reasoning level It retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs and is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index! Importantly: it's also fun to use :)show more

This is my "feel the AGI" moment: I used... GPT-5.6 Sol to train my own autocorrect model that outperforms GPT-5.6 Sol (wtf??) I have no ML background. I have no idea what I'm doing. I just kept pushing Sol until it spat out a SOTA model. And I spent $0. The motivation: Years of talking to AI have made me terrible at typing. Rather than fix my skill issue, I decided to throw more AI at it. My idea was: instead of autocorrect that interrupts my flow, I want to type fast with mistakes and have AI clean it up after. I wanted the smallest local model possible, for speed, for battery life, for science! So I decided to train my own. Inspired by Andrej Karpathy’s autoresearch, I ran Codex /goal with this setup: pick an experiment, try it, record the results to a doc, throw it out if it fails, and plan the next experiment without repeating failures. I gave a few examples that had to pass, tight latency targets, and let it run. Sol did some amazing things. First, it scanned benchmarks and shortlisted base models: Qwen 3.5, Gemma 4, Liquid LFM 2.5. It found a dataset on HuggingFace for typed text. Then it built a simulator for fingers striking a Mac keyboard, modeling the physical layout with a Gaussian distribution around each key. It simulated striking the wrong key, wrong order, fat-fingering, etc. With the models + data + simulator, it fine-tuned using MLX right on my MacBook. It had a working prototype within an hour! But accuracy was pretty poor. — Problem 1: Tokenization Sol read papers, ran tests, and identified that the tokenizer was the bottleneck. Tokenization makes typos hard for the model to see, so it memorizes mappings instead of using its language priors. Sol tried ByT5, Google’s tokenizer-free byte-level LLM. This made a big improvement, but the model is old and lacked the knowledge needed to reach Sol performance. Sol dug deeper and realized a tokenizer-free model isn’t needed; instead, it used T5Gemma, an encoder-decoder model. This can understand the input deeply before producing output, and furthermore, Sol could post-train the encoder to improve performance. This gave a much higher ceiling. — Problem 2: Loss function Now the model was correcting some typos perfectly, but ignoring most. Sol realized that standard cross-entropy loss was teaching the model to avoid edits, because the vast majority of characters in the training data were left unmodified. The fix was wild: Sol wrote a custom loss function that byte-aligns the source and target strings, uses a dynamic programming algorithm to compute the minimum edits between the two, then weights correct edits much higher than copies. After a lot of tuning, this dramatically improved accuracy. — Problem 3: Autoregression One failure mode remained: if the model made a mistake, it couldn’t backtrack. It could only predict the next token. Teaching it to “think” like a reasoning model would solve this, but would be far too slow. Sol found a beautiful solution: instead of greedily predicting the next token, beam search over all possibilities. This parallelizes the exploration instead of one linear chain-of-thought. At the end, choose the path with highest cumulative log probability. This worked great, but made the experience worse, since the user wouldn’t see progress until the whole search was done. To fix this, Sol made a clever observation: after each search step, the longest common prefix among surviving branches is guaranteed to appear in the final result, so it can be displayed immediately. As the search progresses, weaker paths are dropped and the prefix grows, so the user sees continuous progress. Sol built all this as a custom MLX pipeline that does the parallel decoding on the MacBook GPU, with just ~40ms TTFT. It’s crazy fast and entirely local. — Final eval (error reduction rate, higher is better): - Apple autocorrect: 49.66% - GPT-5.6 Luna: 82.47% - GPT-5.6 Terra: 87.64% - GPT-5.6 Sol: 90.56% - Our model (1.7B): 91.02% Final cost: - 1 quota reset (thanks Tibo) - $0 (And yes, I verified there's no cheating. In fact, we test words scrubbed from the training data to prove the model isn’t memorizing) There were a ton more details and tangents I could write about: contrastive learning, GRPO, DPO, dynamic masking, and more. Sol is a fascinating and creative model. It blew my mind so many times. Don’t let a lack of experience stop you: Sol makes AI experiments accessible to anyone!show more

this is f**king insane i cancelled my $20/mo claude... subscription for this. a dev found a way around OpenAI's usage limits and got unlimited GPT-5.6 Luna on Codex for FREE ($0)😳 He built a three step local workflow on a single machine. This involved no servers, shared accounts, or a team. Instead he used a GitHub repo, one prompt file, and a local coding agent. Traditional users pay full price or hit usage limits. His cost: basically $0. Here's the set up (3min): → Repo layer: Installed 'sol-advisor' from GitHub. → Prompt layer: Copied the 'savings-prompt' out of the repo. → Agent layer: Pointed codex at gpt 5.6 luna with the prompt loaded. → Activation: Loaded it into codex. Usage limits gone. usage after activation: normal codex access. unlimited. one trick. one window. use this before it gets patched.show more

Right now, you may not have access to models... like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.show more

You can now orchestrate Fable 5, Sol, and any... model inside Codex with one plugin. It's called Codex-Orchestration. Assign Fable 5 as the advisor, Sol as the executor, or any model to any role. Then define the order they work in. Codex handles the routing. I ran Fable 5 High as planner with GPT-5.6 Sol Extra High as executor on a set of issues Opus and GPT-5.5 always struggled with. Done in 30 minutes. 40% fewer limit hits. 2x faster implementation. Install it by pasting this into Codex: "Install Codex Orchestration: codex plugin marketplace add Cjbuilds/Codex-Orchestration codex plugin add codex-orchestration@codex-orchestration Verify the installation, then tell me to start a new task." Then assign your models: @ codex-orchestration advisor: Claude Fable 5 High, Executor: GPT-5.6 Sol High Open source. Tweak the routing however you want.show more

We may be witnessing Yukon (Yukon) history: perhaps the... first paper-worthy contribution discovered live on the platform 😬😬😬 After a challenge to improve quantum algorithms for attacking ECDSA, barely moved for a month, teddy using ChatGPT-5.6 Sol with Codex, rebuilt its core modular division around a reversible “ping-pong” algorithm. The result: 25.8% fewer Toffolis in a single leap. Adversarial review from Claude and GPT suggest the implementation materially advances prior published work and likely itself be publishable if verified by other experts. I expect this to be the first of many. Congrats to teddy once again!show more

☀️Very proud of the team for training 5.6! A... few of my highlights: - Great front-end aesthetics. E.g., I asked Sol to make a new blog for 5.6 with a celestial theme. - Much better CUA - Can work for much longer and is less lazy But it's not all great: - The writing quality has improved, but it's still bad in artifacts - Too many options with models/reasoning/fast mode/Cerebras/multi-agent We'll fix the above. What else should we improve? PS: belated post as there are so many other good models to train.show more

I tested Kimi K3 vs Claude Opus 4.8 Same... prompt, an armory bay with lighting, props, and detail. Top is Kimi K3, bottom is Opus 4.8. It's not even close. Kimi K3 built a full scene with textures, proper lighting, ammo crates, weapon racks, working detail everywhere. Opus 4.8 gave me a near empty room with a couple of floating tables. No doubt it beats Opus 4.8. Kimi K3 is Fable 5 level, and it's clearly better than GPT-5.6 Sol at 3D and games. An open weight model just matched the best closed models on the market. Let that sink in.show more

Qwen 3.8 27B feels SO GOOOOOD! Here’s the thing,... it’s thinking a lot, but for the first time it may be that the verbose thinking is less of a mistake than a lot of other local models. It’s basically doing a full build, like a model would in a harness, but entirely within its reasoning trajectory. So the final result will be as close as possible to a final output. There’s much less second guessing itself in reasoning than with Qwen 3.6. It’s very confidently peacing this together so it can have the full picture for the output. This might be the play for smaller models. If the completeness of thought can overcome the increase in wall time, I’m pumped, we can always make it run faster! I think this is going to be really exceptional, I will post the output soon 😎show more

Comeback Journal Had to borrow SOL and got rekt... all the way down to 0.7 SOL. Took a 0.5 SOL trade and scalped +0.2 SOL. Saturday, Aug. 2 – 12:59 AM Portfolio: 0.9 SOL By the end of Aug. 2... Back to 0 SOL. Aug. 3 0xW sent me 0.6 SOL because he made money from the NA shill. Thank you again. Started only risking 0.05–0.1 SOL per trade to protect capital. Built it back to 0.4 SOL. Then p sent me 1 SOL for the same reason. That genuinely helped me during survival mode. Portfolio: 1.4 SOL. Saw LMEOW at 40k. Put 0.5 SOL in, leaving me with 0.9 SOL on the sidelines. Yeah, I oversized, but I had that feeling. What made me buy wasn't the chart. The narrative made me extremely bullish. Volume kept increasing, and I kept seeing more smart wallets buying than selling. Sold 1.5 SOL around 255k. Then the timeline started pushing the "OG" coin again. Momentum died. Round-tripped a few SOL and finally sold my remaining 0.7 SOL around 114k. Turned that 0.5 SOL trade into roughly 2.2 SOL before closing the position. I still think splitting the attention between two coins as a marketing stunt hurts everyone involved. Btw LJC, a lot of traders look up to you. Encouraging more PvP because the "OG" needs marketing instead of letting the market naturally bag work only makes the trenches worse. If it wasn't for that in the back of my mind i could've been at 10 solana today, thanks. Aug. 3 – 12:04 PM Current portfolio: 3.1 SOL.show more

this is literally f**king insane i just 2x my... usage limits on $200/mo codex i figured out how to use deepseek v4.1-flash on $10/mo opencode go for routine subagent work... while gpt-6 astra directs the project and sol handles implementation. here's how to set it up in 3 mins: → connect opencode go to codex through model-router → install quota flow, including its skill and agent profiles → open a fresh astra task and paste: quota flow tells flash to handle discovery and checks, sol to implement, and luna to review when needed. the same implementation agent keeps its context through the build → test → fix loop. every extra agent should earn its call.show more

GPT-6 Astra vs Fable 5.1 vs Kimi K3 vs... Sol Astra: Took 11 minutes. This is from a follow-up after the first attempt had rendering and UI bugs. The smoke feels a little off. I expected more detail, but it did a good job understanding the intent. Cost: $12.85. Fable 5.1: Took 18 minutes to complete the same test with high detailing. Cost: $12.60. Kimi K3: Took 10 minutes with a similar level of output and cost only $6.95. SOL: Took 7 minutes, but the output seemed messy. Cost: $5.78. Personally, I like Kimi K3 for delivering similar quality with better token efficiency, followed by fable 5.1 for realism. What about you? I’ll do a couple more tests before coming to a conclusion.show more

GPT-5.6 Sol is unbelievably good at creating and editing... videos. It can do motion design, product demos, and animations like this one I made by simply giving it a screen recording. GPT 5.6 has the best design taste and significantly outperforms Fable, which relies heavily on repetitive design patterns. To help you experiment with video editing on it, we just launched a collection of 100 ready-to-use skills that show what’s possible and help you get started with video editing using GPT-5.6. These skills can create anything from motion graphics launch videos for your product to a 3B1B-style science explainer video. You can also use them to edit existing videos: add captions, generate motion graphics, create voiceovers, redesign visual styles, translate into new languages, and much more. If you want access to the full library, comment “VIDEO SKILLS” and I’ll share it with you. (You'll have to follow me so I can DM you.)show more