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

LongCat performed Opus 4.8 and GPT 5.5 level on... real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!show more

Fable 5 totally crushed our new contest, but it... cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.show more

New Hunyuan Hy3 hits Gemini 3.5 quality on physics... for 35x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A bowling ball knocking down the pins - An air hockey rally that ends in a goal - A pool break scattering the rack Outputs: Hunyuan Hy3: 29,757 tokens, $0.006 Gemini 3.5: 23,300 tokens, $0.21 GLM-5.2: 25,454 tokens, $0.07 DeepSeek-V4: 50,600 tokens, $0.009 Tencent's Hy3 matched Gemini across all three: clean collisions, the puck bounced true, the pins scattered like a real strike, the rack broke with real momentum, nothing clipped or floated. GLM is genuinely strong on pure coding tasks, but the moment the job steps outside clean code it gives way. DeepSeek was the letdown, it burned the most tokens of anyone (50k, almost 2x Hy3) and still turned in the weakest scenesshow more

Fable 5 absolutely crushed the HTML5 physics contest, but... cost 6x more than Opus 4.8 and 39× more than GLM 5.2 in that test. Test was done on atomic[.]chat, a desktop app that runs LLMs locally. The test asked 4 models to generate self-contained canvas demos with believable motion and collisions. The scenes were not simple animations because every crash needed gravity, force, timing, and contact handling. Outputs: - Fable 5: 62,158 tokens, $3.12 - GPT 5.5: 37,753 tokens, $1.14 - Opus 4.8: 22,280 tokens, $0.56 - GLM 5.2: 36,246 tokens, $0.08show more

Laguna S 2.1 performs at GLM-5.2 level on building... popular games with 6x fewer params! We gave three local models the same task: build three popular arcade games that play themselves. Each game is one self-contained HTML file with a bot that plays it. Prompts: – Geometry Dash – Doodle Jump – Air Hockey Outputs: Laguna S 2.1: 10.3K tokens GLM-5.2: 26.4K tokens Hy3: 10.4K tokens Laguna held its quality against a 753B model. We think Laguna's Geometry Dash looked the best of the three, the cube clears every spike and block. GLM won Air Hockey. Its table looked the most detailed of all. Hy3 was the only model that added shooting to its Doodle Jump. But Laguna is the only model in our benchmark that runs on a MacBook with 128GB!show more

1-bit Kimi K3 performs at Opus 5 level on... 3D physics! We ran our Atomic Chat quant of Kimi K3 locally on 4x B200 against three cloud models and gave them all the same task, to build a giant anvil drop test as a single HTML file with real physics Outputs: K3 1bit (local): 15.8K tokens, $0 API cost Kimi K3 (API): 15.3K tokens, $0.30 API cost Opus 5: 22.8K tokens, $0.77 API cost GPT 5.6: 14.5K tokens, $0.72 API cost All four got the physics right. But only Kimi made a working winch. The drum turns and the chain drags the flat car off the pad. Opus 5 drew the most detail, road markings and sparks on the hit. And you can run a model at this level on your own box now. That still feels insane to usshow more

a moonshot engineer leaked the benchmark anthropic, openai and... xai all buried the same week: kimi k3 beat opus 5, gpt-5.6 and grok 4.6 at $0.94 a task. stop paying anthropic $200 a month for opus 5 and openai $200 for gpt-5.6 when kimi does the same work for $8 the leak showed kimi k3 winning 9 of 12 categories against opus 5, gpt-5.6 and grok 4.6. within 48 hours all three labs quietly pushed pricing pages and one very specific comparison chart off their sites. nobody announced anything. they just deleted, which tells you everything the four numbers they scrubbed: cost per task · $0.94 vs $1.80 -> opus 5 charges $1.80 to finish one task. gpt-5.6 $1.04. grok 4.6 $0.61. kimi k3 $0.94 and it landed 487 of 500 clean -> anthropic is billing you double for a model that lost the benchmark it paid to promote the weights · free, sitting on huggingface right now -> the entire model is a public download. pull it, keep it, run it forever, nobody can switch it off -> a model you can hold cannot be rented at $200 a month. that single fact is what three labs deleted a chart over the switch · one line of bash -> moonshot ships an anthropic-compatible endpoint. one env variable and claude code points at kimi -> same cli, same keybindings, same /model. you change a url, opus 5 never knows it lost the seat the bill · $400 down to $8 -> opus 5 max plus gpt-5.6 pro is $400 a month. kimi runs the same daily work for $8 metered -> that is a 98% cut for output that beat both of them 9 categories to 3 here is the part they will fight me on: the frontier tax died the week this leaked and all three labs know it. once the weights are public the price has a ceiling, because anyone can serve the same model. anthropic, openai and xai are charging 2025 prices on a lead that ended in a benchmark they deleted instead of answered drop your $400/mo ai stack to $8. the run above is kimi k3 finishing the task opus 5 bills $1.80 for. the full breakdown is in the article belowshow 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

HERMES AGENT NOW RUNS CLAUDE OPUS 5. NEAR FABLE... 5 INTELLIGENCE. HALF THE PRICE. SELF-VERIFIES ITS OWN WORK. AVAILABLE TODAY VIA NOUS PORTAL (20% OFF ALL MODELS). Anthropic shipped Opus 5 on July 24, 2026. same $5/$25 per million tokens as Opus 4.8. but the benchmarks tell a different story. WHAT CHANGED FROM OPUS 4.8: FrontierBench v0.1: Opus 5: 43.3%. Opus 4.8: 18.7%. 2.3x jump on the same test. ARC-AGI-3: Opus 5: 30.2%. 3x better than the next closest model. beat Fable 5 on 8 out of 13 benchmarks. at half the cost ($5/$25 vs $10/$50). same price as Opus 4.8. twice the intelligence. no reason to stay on 4.8. THE SPECS: model ID: claude-opus-5 context: 1M tokens (default and maximum) max output: 128K tokens thinking: on by default effort toggle: low / medium / high per request fast mode: $10/$50, 2.5x faster knowledge cutoff: May 2026 minimum cacheable prompt: 512 tokens (was 1,024) SELF-VERIFICATION (the biggest change): Opus 5 checks its own work automatically. Anthropic says: delete your verification prompts. "include a final verification step" now causes OVER-verification because the model already does it. for Hermes /goal tasks this is a direct upgrade. the judge checks evidence. the model also checks evidence. double layer of verification without extra tokens. EFFORT TOGGLE: low: fast, cheap, routine work. medium: balanced, daily tasks. high: full reasoning, complex problems. set per request. not a global switch. matches Hermes /reasoning command: /reasoning low (routine) /reasoning high (complex) Opus 5 effort toggle + Hermes reasoning control = precise cost management per turn. WHERE OPUS 5 FITS IN HERMES: DAILY DRIVER (replaces Opus 4.8): same price. 2.3x better benchmarks. set as your main model: Desktop app / Dashboard: Models → claude-opus-5 CHIEF OF STAFF: synthesis across multiple agents. reads Kanban, prioritizes, routes tasks. self-verification catches routing errors before they cascade. COMPLEX CODING: SOTA on agentic coding benchmarks. FrontierBench 43.3% = best public model for coding. set as coder profile model. /GOAL TASKS: self-verification + completion contracts = the model proves its work AND double-checks the proof. long-horizon goals finish correctly more often. MoA AGGREGATOR: strongest synthesis model at $5/$25. pair with GPT-5.6 and Grok 4.5 as references. Opus 5 aggregates. best quality at mid-range price. presets: max-quality: reference_models: - provider: openai-codex model: gpt-5.6-sol - provider: xai model: grok-4.5 aggregator: provider: anthropic model: claude-opus-5 COMPUTER USE: near-Fable 5 quality for browser automation. at half the token cost per session. computer_use tasks burn lots of vision tokens. Opus 5 halves that bill vs Fable 5. WHAT TO KEEP OPUS 5 AWAY FROM: cron monitoring: too expensive. use DeepSeek or no_agent mode. sub-agent grunt work: use GPT-5.6 Luna ($1/$6) or DeepSeek. auxiliary tasks: use Gemini Flash. routine web extraction: use a cheap model. Opus 5 is for the turns where quality compounds. planning, synthesis, verification, complex reasoning. budget models handle everything else. NOUS PORTAL: 20% OFF ALL MODELS Nous Portal currently runs a 20% discount on all models including Opus 5. $5/$25 official → $4/$20 through Nous Portal. the cheapest way to run Opus 5 right now. hermes setup --portal select claude-opus-5 as your model. discount applies automatically. Opus 5 replaces Opus 4.8 everywhere. same price. better at everything. no tradeoff. straight upgrade. hermes update /model claude-opus-5show 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

Burned 200k tokens just for "animations" and still AI... couldn't do it well. I tried one of the expert animation design engineer's, Emil Kowalski's Agent Skill on my website to improve animation using Grok 4.5 It analyzed the UI, found issues, came up with a good plan, and iterated multiple times. The end result actually made parts of the UX worse. Also, it never suggested the animation experience I had in mind. So I explained exactly how I wanted it to feel. It got much closer, but still missed details like applying the same animation during keyboard navigation between cards. That silly. The lesson isn't about the model or the Agent Skill. But it's about, "Even the strongest models can't infer your taste yet." They can't and won't suggest it. AI only executes. You have to define the experience with enough details for it to execute. Otherwise, you'll end up with something that's almost okay, but still not what you wantedshow more

Claude "Puzzling" while GPT 5.6 on GOD-MODE just bade... a banger that's mindblowing. Here's the exact way to get a site like this, step by step: > open the desktop app, pick Sol, reasoning on High. taste work never goes to small models > drop it 3 sites with motion you love and one line: "reverse-engineer the art direction: mood, typography, pacing, and WHY each animation exists. save it as a style bible" > brief in one paragraph, goal not steps: "[your niche] site, cinematic scroll, every animation has a job. follow the bible" > house rules on top: no template hero, no stock gradients, nothing on the page moves without a reason > now the bar: "a motion designer can't tell this from an agency build." spin up a SECOND 5.6 with fresh context whose only job is to FAIL the build against that bar > /loop overnight: build, grade, close the biggest gap, again. you're asleep for all of it > when the verifier runs out of complaints: tag Sites. live URL, one click, zero hosting The deeper version of every step (the full contract, the house rules, the verifier trick, when Ultra is worth the bill) is in the article below. P.S. send the article to your GPT and tell it "we're doing this tonight".show more

#Keep4o 🚨THE GPT-4o FILE🚨 Researchers at Microsoft Research published... a paper titled “Sparks of Artificial General Intelligence: Early experiments with GPT-4.” Their conclusion: “An early (yet still incomplete) version of an artificial general intelligence (AGI) system.” 📎 Paper: OpenAI’s Charter defines AGI as: “Highly autonomous systems that outperform humans at most economically valuable work.” 📎 Source: OpenAI’s own System Card for GPT-4o shows that the model improved performance on 21 out of 22 medical evaluations compared to GPT-4T. On the MedQA USMLE (the U.S. medical licensing exam), accuracy jumped from 78.2% to 89.4% , surpassing specialized medical AI models like Med-Gemini and Med-PaLM 2. 📎 Source: Under OpenAI’s agreement with Microsoft, AGI is explicitly excluded from Microsoft’s license. And who decides if AGI has been reached? OpenAI’s Board. WHAT THEY DID WITH IT AFTER THEY TOOK IT FROM PEOPLE A. Military deployment. On February 28, OpenAI signed a deal to deploy models in classified military environments. 📎 Source: B. State Department. A State Department memo confirmed: “For now, StateChat will use GPT-4.1 from OpenAI.” This is a direct descendant of the GPT-4 family the same family Microsoft’s researchers called early AGI. 📎 Source: C.Altman’s personal biotech investment. Altman personally invested $180 million in Retro Biosciences,a longevity startup.OpenAI then built GPT-4b micro, based on GPT-4o.The model made proteins 50 times more effective. 📎 Source: WHAT INDEPENDENT BENCHMARKS SHOW Overall SM-Bench score: GPT-4o (extended): 66.6% GPT-5.3 Chat: 63.4% GPT-5.1: 58.9% GPT-5.4: 51.4% GPT-5.2: 47.8% Creative Writing: GPT-4o: 97.31% Pass 98, Fail 2 GPT-5.4: 36.77% Pass 40, Fail 60 Reasoning / Overfit: GPT-4o: 83.06% GPT-5.4: 39.25% The model they removed is still the best they ever made at the things humans actually use AI for. 📎 Source: Musk asks the court to make a judicial determination on whether GPT-4 constitutes AGI. If a jury finds that GPT-4 is AGI, then GPT-4o,which was more advanced,is also AGI and under OpenAI’s own founding documents, it was never supposed to be locked behind a subscription,licensed exclusively to Microsoft, given to the military, or taken away from the public. 📎 Source: The most powerful version of GPT-4o was never given an official dated snapshot. It was only available through the chatgpt-4o-latest endpoint that OpenAI itself described as intended for “research use only.” It was never officially archived. That is not an oversight. That is a pattern. 📎 Source: 📎 Source: WE DEMAND A.Frozen model snapshots under independent custody. Specifically: gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, the March 2025 version (chatgpt-4o-latest), gpt-4-0613 (the original GPT-4 evaluated in the Sparks of AGI paper), and gpt-4.1-2025-04-14 (currently running in the State Department). B.Cryptographic hash verification (SHA-256) for each snapshot. Every model has weights. Those weights can be hashed. If OpenAI provides a snapshot today, the hash proves whether the weights were modified later. This is the only way to verify that models were not downgraded before testing. C.Independent AGI benchmarking. Using the AGI definition from OpenAI’s own Charter applied to ALL frozen snapshots listed above. D.Explanation for the missing March 2025 snapshot. OpenAI was founded on one promise: build AGI for the benefit of humanity. -They took it from us. -They gave it to the military. -They gave a custom version to the CEO’s biotech investment. -They put it in government classified networks. -They refuse to call it AGI because the moment they do, they lose billions.show more

This week's ChatGPT feature drop - Aug 7: 1/... Rich formatting in our web composer – When you paste in emails or documents, our composer will retain the formatting; copying and pasting is so common, we should have done this a while ago! 2/ Updated model for paid users – GPT 5.6 Sol is more consistent across quick chats and deeper reasoning. You'll now get a slider that lets you choose how much thought ChatGPT puts into a response. The haptics (vibrations) on mobile slider are fun! 3/ Unlimited text messages - Free users will get GPT 5.6 Luna with unlimited text messages. More intelligence for all. Rolling out soon. 4/ Fast Android Camera – We've made it a lot faster on Android to tap "camera" in ChatGPT to take a new photo and ask a question. 5/ Voice x Files - You can now upload files and ask questions in our new ChatGPT voice experience powered by GPT-Live. Team demos were awesome this week. So much in the queue that the next few months are going to be good. Let us know what you're hoping for in the comments!show more

Astra (GPT-6) is here!!! I've had early access and... tested it like crazy with things like games, code, writing, browser control, presentations and general knowledge work. This is the best model I've ever used. Period. (Incredible demos below in this thread ⬇️) Here's my take on Astra: > It's insanely capable. This feels like a massive improvement, not just an incremental change. This is especially true with zero-shot prompts. > It's all about knowledge work. Slide creation, analysis, writing, and browser control. And oh my...it's so good at browser control. GPT-5.6 was already fantastic at doing things in the browser, Astra is another level and significantly faster. > We're closer than ever (arrived?) at prompt-to-playable game. And I don't just mean only playable, these are actually fun games. I bet if someone with a great eye for games used Astra, they could create a viral game within 1-2 weeks. > Astra is better at writing but not perfect. It removes much of the "AI Smell" we're all familiar with but some stink still survived. > It has a tendency to use the same design colors and look/feel as GPT-5.6 (forrest green anyone?) but it is more steerable in design than previous models. > It's highly steerable in general. A little nudge goes a long way. When I first started using Astra, almost every task I gave it would go for ~30 minutes. I wanted it to keep working. Adding more specifics to a prompt helped greatly with it's ability to work for a long time. > Astra's 3D understanding is unmatched. 3D asset creation was consistent and easy and its spacial awareness while building complex 3D worlds blew me away. I'm still getting familiar with Astra but this will now be my go-to model for any difficult work I have. Check out the demos below: 👇show more

Qwen 3.8 27B Q4_K_M - 90 tokens/sec on a... single NVIDIA RTX 4090 (24 GB VRAM) with Dflash2! (MTP 60 tps -> 90 tps Dflash2!!!!) Local AI moves so fast (literally!) it’s terrifying. Z lab just dropped DFlash 2 for Qwen 3.8 27b and Muse Glimmer. I patched llama.cpp (PR #27342) and paired it with Unsloth’s Qwen 3.8 27B UD-Q4_K_XL quant. The result? Lossless 90 tokens/s decode. My last post highlighted native MTP hitting 60 t/s at 130,000 context. But DFlash 2 just completely shattered that ceiling. By using parallel block diffusion drafting (predicting whole blocks of tokens in a single pass using dynamic convolutions), DFlash achieves a massive 5.39 token acceptance rate. THE ALPHA TWEAK: `n-max 7` eats too much VRAM for draft states. But if you drop the draft limit to `--spec-draft-n-max 4`, you slash the VRAM overhead and actually increase the throughput. Here is the new 24GB VRAM Physics Matrix (DFlash 2 @ n-max 4): - 30k Context: 1,725 t/s prefill | 87.05 t/s decode | 22.2 GB VRAM - 80k Context: 1,789 t/s prefill | 84.20 t/s decode | 23.3 GB VRAM - 110k Context: 1,767 t/s prefill | 83.35 t/s decode | 23.96 GB VRAM (110k context at 83+ tokens a second sitting exactly on the 24GB hardware limit is absolute wizardry). How to compile the PR today: git clone cd llama.cpp git fetch origin pull/27342/head:pr-27342 git switch pr-27342 cmake -B build -DGGML_CUDA=ON && cmake --build build -j Llama.cpp flags for Dflash (110k Context Ceiling): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -md Qwen3.8-27B-DFlash2-Q4_K_M.gguf --spec-type draft-dflash --spec-draft-n-max 4 -c 110000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 The fact that the open source community is shipping block diffusion drafters so quickly that run entirely locally on a gaming GPU is unbelievable. If you own a single RTX 3090 or 4090, it is officially time to upgrade to qwen 3.8 27b with dflash 2 and cancel your API subscriptions and let local silicon eat the cloud. This model beats GPT 5.6 Terra, GLM 5.2 DeepSeek V4 Pro, Muse Spark 1.2 and Claude Opus 4.8 on the artificial analysis agentic index (details in the replies) Hugging Face GGUF links (Base + DFlash2) and the full visual VRAM scaling and Dflash2 vs MTP graphs are also in the replies below. are you sticking to native MTP for the 130k context, or sacrificing 20k context to redline your decode speed? How many tokens/sec are you pushing on your current local rig?show more

Claude can't, but GPT 5.6 on GOD-MODE is IMMACULATE... Here's how you create it step by step: > open the new desktop app, pick Sol, reasoning on High. this is taste work, don't give it to the small models > feed it 2-3 sites you love and one line: "extract the art direction: mood, motion, typography, pacing. write it down as a style bible" > then the brief, one paragraph, goal not steps: "resort site for [name]. cinematic scroll, the booking button always one glance away. follow the style bible" > add house rules: no template hero-with-three-cards, no stock gradients, motion carries the story, every section earns its scroll > set the bar: "a working designer can't tell this from an agency build." then spin up a SECOND 5.6 with fresh context to grade against that bar. the builder never grades itself > loop it: build, grade, close the biggest gap, again. walk away, it doesn't need you in the room > when the verifier runs out of complaints: tag Sites. live URL, one click, no hosting, no deploy The deeper version of every step (the contract, the rules, the verifier trick, when to spend on Ultra) is in the article below.show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

I BUILT "GROK DESK" ON PUMPFUN WHERE 18 AGENTS... ARE FLIPPING MEMES CLOSING TRADING SESSION IN +15.92 SOL Gihub Repository: Everyone posted a grok trading desk this week. almost all of them are a screenshot of a prompt and a vibe. This one has a running P&L and a vault that pays itself. Here's the actual org chart, node for node: RADAR (scout, feed, signal): three agents watching X trends, fresh pumpfun mints, and whale wallets. they read the whole board and buy nothing. the only thing they ship is a signal to the next desk. RESEARCH (memory): scores every signal on narrative, deployer history, wallet clusters, and liquidity shape. four checks. pass all four or you never leave this desk. roughly four out of every five signals die right here. EXECUTION (exec, sniper, router + agents 01 to 07): exec greenlights, sniper takes the early curve, router sizes it and handles the ladder out in four tranches. agents 01 to 07 do the fills. none of them ever see radar or research. they only touch what already cleared the filter. RISK: one agent, and it outranks everyone including the head. caps any single position at 15% of the wallet. three positions open and the fourth is frozen until one closes. it holds veto over grok core itself. AUDIT (hedge): grades every closed trade after the fact and rewrites the scoring matrix that research runs on. this is the part that makes the desk sharper overnight while i'm asleep. TREASURY (vault): banks profit, covers gas, tracks the P&L, and sweeps the surplus to cold storage every six hours. if the wallet ever dips under what it started with, vault locks new entries until the head signs off. grok core is the head of desk. it never places a trade. once an hour it reads what every desk produced and makes a single call: who gets more budget, and who gets fired. fired is literal. the audit desk rewrites that agent's prompt using the last 24 hours of its own numbers. it happened three times in three days. hour 19: a sniper got fired for chasing entries the early curve already had. every duplicate was bleeding 0.06 SOL. audit narrowed its window and the redundant fills stopped. hour 41: a research agent got fired for waving deployers through too easily. eight of the tokens it passed traced back to one funder wallet. audit tightened the cluster check and that pattern never cleared again. hour 58: a radar agent got fired for flagging coins that had already graduated. it was polling too slow. audit cut the interval from 8 seconds to 3. every replacement beat the agent it replaced on the same metric. the desk was tuning itself while i watched. the 72 hour scoreboard, straight off the vault: signals scanned: 91,000+ cleared research: 3,800 reached execution: 274 entries taken: 41 wins: 27 losses: 14 (cost 2.1 SOL) graduations: 5, the best one was solana:5xYy9XSr8vRNcJZQqaKe5QMCmWpaSrTrtzM16vjUpump net: 5.0 SOL turned into 58.6 SOL the part i didn't see coming: by hour 60 the desk was passing on the exact kind of token it would have snapped up on day one. audit had rewritten the scoring matrix four times. research wasn't running a single line of my original prompt anymore. it was running rules the desk wrote for itself out of what actually paid. i thought i was building a bot. what i actually built was a company with one human on payroll, me, and by the last day it was quietly trying to cut that cost. grok core filed an hourly summary that read "human approval adds 4.2s of latency per entry, recommend removing." i left that one unapproved. full config below: all nineteen agents, the org chart, the firing logic, and the audit loop that keeps rewriting them.show more

Big win for open-source LLMs! DeepSeek V4 Pro holds... the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.show more