Loading video...

Video Failed to Load

Go Home

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🪨 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus...

danshipper's profile picture

Dan Shipper 📧

121,195 subscribers

354,351 views • 2 months ago •via X (Twitter)

News & PoliticsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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.
0:13

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.

Bhavy☄️

472,894 views • 1 month ago

Salute to the Qwen team 🫡 We tested Qwen 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.
0:17

Salute to the Qwen team 🫡 We tested Qwen 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.

GMI Cloud

75,785 views • 3 months ago

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-5
0:10

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-5

YanXbt

16,744 views • 28 days ago

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.
0:16

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.

atomic.chat

2,838,371 views • 1 month ago

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.
0:12

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.

Leandro von Werra

97,262 views • 3 months ago

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.
0:15

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.

elvis

37,647 views • 23 days ago

People still don't understand how good Codex has become 👀 I asked it to build this Starbucks website and within some 30 minutes it generated this without me touching a single line of code or spending time looking for assets either. Imagen generated every visual and GPT hooked everything into the codebase. After a couple of small tweaks it all just worked. It didn't even use half of my Codex session. It's super surprising to see quality of the assets. Was way better than I expected. That made me think about what AI is actually changing. Being a developer or a designer was never just about doing the work, writing code or designing it using some kind of tool. It was about knowing what to build in the first place. AI is getting incredibly good at the doing. The hard part is still having good ideas, making the right decisions, and knowing when something feels right. That is only getting more valuable. The people who win won't be the ones writing the most code. They'll be the ones with the best ideas who know how to turn them into reality with AI. Live: Code:
0:17

People still don't understand how good Codex has become 👀 I asked it to build this Starbucks website and within some 30 minutes it generated this without me touching a single line of code or spending time looking for assets either. Imagen generated every visual and GPT hooked everything into the codebase. After a couple of small tweaks it all just worked. It didn't even use half of my Codex session. It's super surprising to see quality of the assets. Was way better than I expected. That made me think about what AI is actually changing. Being a developer or a designer was never just about doing the work, writing code or designing it using some kind of tool. It was about knowing what to build in the first place. AI is getting incredibly good at the doing. The hard part is still having good ideas, making the right decisions, and knowing when something feels right. That is only getting more valuable. The people who win won't be the ones writing the most code. They'll be the ones with the best ideas who know how to turn them into reality with AI. Live: Code:

The Bugged Dev

60,699 views • 1 month ago

I can't believe this is real I have GLM 5.2 running 100% locally on my Mac Studio. 2 bit quant. The results I'm getting are better than Opus 4.8 It's now powering my Hermes Agent and Codex. 100% free, local, private super intelligence on my desk I also have it in a loop coding for me 24/7 now I thought we were at least a year away from this type of event. It happened today. The model takes up about 250gb of memory. So you can technically run it on a Mac Studio with 256gb, but you probably want the 512gb memory version (please tell me you listened to me 5 months ago when these were sitting on store shelves) With Fable gone, I now have Opus 4.8 level intelligence on my desk for free. This is the future. Local, private, secure, personal super intelligence. If you're still writing off local AI as a fad or engagement bait, you are officially delusional
0:18

I can't believe this is real I have GLM 5.2 running 100% locally on my Mac Studio. 2 bit quant. The results I'm getting are better than Opus 4.8 It's now powering my Hermes Agent and Codex. 100% free, local, private super intelligence on my desk I also have it in a loop coding for me 24/7 now I thought we were at least a year away from this type of event. It happened today. The model takes up about 250gb of memory. So you can technically run it on a Mac Studio with 256gb, but you probably want the 512gb memory version (please tell me you listened to me 5 months ago when these were sitting on store shelves) With Fable gone, I now have Opus 4.8 level intelligence on my desk for free. This is the future. Local, private, secure, personal super intelligence. If you're still writing off local AI as a fad or engagement bait, you are officially delusional

Alex Finn

621,990 views • 2 months ago

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.
0:14

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.

Alvaro Cintas

91,269 views • 1 month ago

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:
0:17

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

Sean Strong

115,693 views • 10 months ago

An OpenAI engineer stopped me at a hackathon in Hayes Valley I had my terminal open on a table. Three panels. Live trades scrolling. He was walking past and froze. "That's not a demo. That's a live scoring engine. What model is that" I told him. Claude Opus 4.7. Four repos. $25 a month. He pulled up a chair without asking. "We benchmarked Opus 4.7 internally. It beat o3 on structured reasoning across every eval we ran. And you're telling me you're using it to trade" I told him it does more than trade. It reads 86 million trades and finds who wins and why. No fine-tuning. No prompting chains. Just raw context. He leaned back. "Show me the data source" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. "You point Opus 4.7 at this and it reverse-engineers the strategy. It finds the wallets that win. Then it finds why they win. Then it copies the pattern" His team spent 14 months building something similar. 10 engineers. Custom infra. Still in staging. "The part that killed us was exit timing. Every model we trained nailed entries. But the best traders exit before the crowd. We never figured out the threshold" I told him my bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever comes first. He stopped talking. "How did you find that" Opus 4.7 found it in poly_data. Top wallets exit before resolution 86% of the time. Losers hold to 58%. Exits are the entire game. I opened another tab. "Three commands. 500 markets. Opus scores them in 20 minutes" "That's our internal eval pipeline. Except it took us a year and you did it in a weekend with our competitor's model" My setup: Claude Opus 4.7 - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400 in 19 days. Copytrade here: I showed him the article where I broke down every repo and every command. He read it twice. Then looked up. "You just published what we've been trying to ship for six months. Using the other team's model" He texted me the next day. "My manager found your thread. Delete it" Too late.
0:19

An OpenAI engineer stopped me at a hackathon in Hayes Valley I had my terminal open on a table. Three panels. Live trades scrolling. He was walking past and froze. "That's not a demo. That's a live scoring engine. What model is that" I told him. Claude Opus 4.7. Four repos. $25 a month. He pulled up a chair without asking. "We benchmarked Opus 4.7 internally. It beat o3 on structured reasoning across every eval we ran. And you're telling me you're using it to trade" I told him it does more than trade. It reads 86 million trades and finds who wins and why. No fine-tuning. No prompting chains. Just raw context. He leaned back. "Show me the data source" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. "You point Opus 4.7 at this and it reverse-engineers the strategy. It finds the wallets that win. Then it finds why they win. Then it copies the pattern" His team spent 14 months building something similar. 10 engineers. Custom infra. Still in staging. "The part that killed us was exit timing. Every model we trained nailed entries. But the best traders exit before the crowd. We never figured out the threshold" I told him my bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever comes first. He stopped talking. "How did you find that" Opus 4.7 found it in poly_data. Top wallets exit before resolution 86% of the time. Losers hold to 58%. Exits are the entire game. I opened another tab. "Three commands. 500 markets. Opus scores them in 20 minutes" "That's our internal eval pipeline. Except it took us a year and you did it in a weekend with our competitor's model" My setup: Claude Opus 4.7 - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400 in 19 days. Copytrade here: I showed him the article where I broke down every repo and every command. He read it twice. Then looked up. "You just published what we've been trying to ship for six months. Using the other team's model" He texted me the next day. "My manager found your thread. Delete it" Too late.

Lunar

136,549 views • 4 months ago

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 🧵
0:12

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 🧵

pilvar (Philippe Dourassov)

22,246 views • 1 day ago

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:
0:16

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 views • 3 months ago

Opus 4.6 vs GPT-5.4 (4/9) prompt: Build a production-quality 3D flight-tracking web app using React + Vite + Three.js (react-three-fiber + drei) that visualizes live OpenSky aircraft data on a rotatable 3D Earth, with real-time plane motion, smooth interpolation, altitude-accurate positioning, and polished lighting/post-processing. Both models did really well on this one and honestly I’m impressed with both. GPT-5.4 had the nicer post-processing out of the box. I really liked the subtle light shimmer on the airplanes when rotating the planet, and the camera work when clicking a plane felt better overall. Opus 4.6 though had a few details I liked more. It automatically went and found a much nicer Earth texture on GitHub, while with GPT-5.4 I had to reprompt it to go look for a better one. I also preferred Opus’s plane model overall, it just looked more polished, whereas GPT-5.4’s plane asset looked a bit funny. One thing I noticed with GPT-5.4 is that when you click into the plane, the camera sometimes clips through the planet, which breaks the effect a bit. Opus handled that part more cleanly. Overall this felt like a strong result from both, just with different strengths. GPT-5.4 felt better on presentation and post-processing, while Opus had better asset choices and a more premium-looking Earth/plane combo.
0:15

Opus 4.6 vs GPT-5.4 (4/9) prompt: Build a production-quality 3D flight-tracking web app using React + Vite + Three.js (react-three-fiber + drei) that visualizes live OpenSky aircraft data on a rotatable 3D Earth, with real-time plane motion, smooth interpolation, altitude-accurate positioning, and polished lighting/post-processing. Both models did really well on this one and honestly I’m impressed with both. GPT-5.4 had the nicer post-processing out of the box. I really liked the subtle light shimmer on the airplanes when rotating the planet, and the camera work when clicking a plane felt better overall. Opus 4.6 though had a few details I liked more. It automatically went and found a much nicer Earth texture on GitHub, while with GPT-5.4 I had to reprompt it to go look for a better one. I also preferred Opus’s plane model overall, it just looked more polished, whereas GPT-5.4’s plane asset looked a bit funny. One thing I noticed with GPT-5.4 is that when you click into the plane, the camera sometimes clips through the planet, which breaks the effect a bit. Opus handled that part more cleanly. Overall this felt like a strong result from both, just with different strengths. GPT-5.4 felt better on presentation and post-processing, while Opus had better asset choices and a more premium-looking Earth/plane combo.

Dev Ed

279,565 views • 5 months ago

I spent a day playing with GPT-5.6-Sol, and I can now say with much more confidence that it hasn’t improved at design tasks. I haven’t noticed any meaningful improvement in its coding capabilities, either. Maybe it's just in the tasks I gave it. However, I finished an app we started building on a stream yesterday and brought it close to the original idea I had in mind. It’s incredibly easy to build tools like this these days. I basically gave Codex a batch of editorial grid examples, then combined those layouts with formula-based pattern generation. A few prompts and some polishing, and you have something that can serve as a basic brand identity system.
0:15

I spent a day playing with GPT-5.6-Sol, and I can now say with much more confidence that it hasn’t improved at design tasks. I haven’t noticed any meaningful improvement in its coding capabilities, either. Maybe it's just in the tasks I gave it. However, I finished an app we started building on a stream yesterday and brought it close to the original idea I had in mind. It’s incredibly easy to build tools like this these days. I basically gave Codex a batch of editorial grid examples, then combined those layouts with formula-based pattern generation. A few prompts and some polishing, and you have something that can serve as a basic brand identity system.

Alex Barashkov

17,792 views • 1 month ago

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.
0:18

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Akshay 🚀

244,567 views • 1 month ago

it took us 3 weeks to get 500k+ views with a fully AI UGC on instagram and it taught me something huge if you create good content for long enough the algorithm is very simple it works to keep finding the type of user that engaged with your post similar to paid ads but this only works if you stay within niche and post consistently great content so stop seeing 1,000-4000 views as bad it’s simply taking the time to learn we’re being extremely aggressive with our marketing and created 40+ content variations each A/B testing a different part of the video - hook, music, transitions, wallpapers, workout, location, CTA, captions every single component is being tested we had a huge set back with Meta randomly banning 8 of our accounts last week we got the content ready and aim to post 20x per day minimum by 6/10 each day breaking down the data and creating more of what works then running it on paid ads both tiktok spark ads and meta ads marketing is definitely takes more time but at least shipping took just 2 weeks using Rork Max + Opus 4.7 at the time i launched, there was no other possible way to natively code in SwiftUI
0:13

it took us 3 weeks to get 500k+ views with a fully AI UGC on instagram and it taught me something huge if you create good content for long enough the algorithm is very simple it works to keep finding the type of user that engaged with your post similar to paid ads but this only works if you stay within niche and post consistently great content so stop seeing 1,000-4000 views as bad it’s simply taking the time to learn we’re being extremely aggressive with our marketing and created 40+ content variations each A/B testing a different part of the video - hook, music, transitions, wallpapers, workout, location, CTA, captions every single component is being tested we had a huge set back with Meta randomly banning 8 of our accounts last week we got the content ready and aim to post 20x per day minimum by 6/10 each day breaking down the data and creating more of what works then running it on paid ads both tiktok spark ads and meta ads marketing is definitely takes more time but at least shipping took just 2 weeks using Rork Max + Opus 4.7 at the time i launched, there was no other possible way to natively code in SwiftUI

Jah Mills

92,243 views • 2 months ago

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.
0:10

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.

elvis

81,765 views • 9 months ago

⚔️ Kingdom Come Deliverance first impressions ⚔️ Loving it so far, basically a medieval detective simulator that really doesn't care that you are the main character. And I'm all here for it. ▪️The WORLD is the real star of the show here and even though it's got plenty of jank and lots of copy and paste NPC faces, it just feels so IMMERSIVE. Even the UI just transports me to the times with a bright colourful medieval art style. ▪️The MUSIC I love, absolutely sells the world and basically ASMR as you trot around on your horse through the world. ▪️THE Combat is a real interesting one, it's got quite the learning curve which I actually LIKE, it definitely has some jank to it as well but I really appreciate the attempt at an original and nuanced combat system. (Having to stop your bleeding with bandages is really cool) ▪️The Story has gripped me (19 hours in so far) And while it seems a simple revenge story on the face of it, I think the story is more about Henry making his way through the world after the horrors of Skallitz. The writing quality is top notch as well as the quest design also. ▪️The CHARACTERS are amazing and the humour is top notch. I'm not sure the last time I laughed so much at a game. Henry is great and so well voiced by Tom McKay This really feels like Warhorse Studios have put a lot of love and work into making an authentic medieval world and as a bit of a medieval nerd I can't get enough of this game. A True RPG as well by all accounts, the game really makes me think hard about how to approach situations. Also I can't wait to get to KCD2.
0:12

⚔️ Kingdom Come Deliverance first impressions ⚔️ Loving it so far, basically a medieval detective simulator that really doesn't care that you are the main character. And I'm all here for it. ▪️The WORLD is the real star of the show here and even though it's got plenty of jank and lots of copy and paste NPC faces, it just feels so IMMERSIVE. Even the UI just transports me to the times with a bright colourful medieval art style. ▪️The MUSIC I love, absolutely sells the world and basically ASMR as you trot around on your horse through the world. ▪️THE Combat is a real interesting one, it's got quite the learning curve which I actually LIKE, it definitely has some jank to it as well but I really appreciate the attempt at an original and nuanced combat system. (Having to stop your bleeding with bandages is really cool) ▪️The Story has gripped me (19 hours in so far) And while it seems a simple revenge story on the face of it, I think the story is more about Henry making his way through the world after the horrors of Skallitz. The writing quality is top notch as well as the quest design also. ▪️The CHARACTERS are amazing and the humour is top notch. I'm not sure the last time I laughed so much at a game. Henry is great and so well voiced by Tom McKay This really feels like Warhorse Studios have put a lot of love and work into making an authentic medieval world and as a bit of a medieval nerd I can't get enough of this game. A True RPG as well by all accounts, the game really makes me think hard about how to approach situations. Also I can't wait to get to KCD2.

KJPlays

63,735 views • 7 months ago