We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container.
So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added them to the Cline harness.
TL;DR of this special prompting:
- Trust source code over the user prompt, so read every call site and existing tests before starting the task
- Weigh edge and error cases as heavily as the happy path
- Always reproduce the bug before fixing
- Don't trust the first passing test suite, and verify suspicious looking half-baked tests
- Never stop at just editing, keep working until the change is verified complete.
We then asked this modified harness to fix a real bug from our repo, and compared the results to the original Cline agent harness.
Results:
- Used 2.7x fewer tokens (19.7M → 7.2M)
- Finished 2x faster (49min → 24min)
- Cost 2.4x less ($7.69 → $3.25)
Same Muse Spark 1.2 model, same task, only the prompting changed. Incredible how much of a performance gain Meta was able to achieve training it on these special instructions!
显示更多
"Voice gets interesting the moment developers find interaction patterns that only voice makes possible." -
@scottcjohnston
We built a
@DeepLearningAI course on exactly that. Voice for AI Agents and Applications, with
@_ashwyn ,
@AndrewYNg , and
@scottcjohnston.
Most voice infrastructure out there was built for one job: replace humans in contact centers. Answer the phone, follow the script, close the ticket.
Building voice into a real product is a different problem. This free short course is about that, giving your apps and agents an actual voice.
You'll walk away having built:
🎮 a voice-interactive game where voice and mouse clicks run over one channel
🤖 a chat agent that gains a voice in ~10 lines, no touching your prompts, RAG, or tools
📞 an agent that makes real outbound phone calls and streams the transcript back live
Enroll for free:
We'd love to see what you build. Let's go 🚀
显示更多
Watch the full recording of our Q2 2026 earnings call.
Prepared Remarks
00:00:00 - Welcome
00:01:20 - 843,775 BTC, 203,683 sats per share, $17B raised year to date, and Strategy’s position as the largest institutional holder of Bitcoin
00:03:27 - Q2 balance sheet: $49.7B of digital assets, $3.75B current USD reserve, lower debt, higher preferred equity, and strong stress-case coverage
00:08:57 - Bitcoin KPIs: 4.5% BTC Yield, 29,997 BTC Gain, and ~3.6x growth in Bitcoin per share since 2020
00:12:47 - Q2 execution: higher Bitcoin holdings, lower debt, larger USD reserves, stronger Bitcoin per share, and active capital management
00:15:03 - Strategy as a net buyer of Bitcoin and net issuer of Digital Credit: 48x more BTC bought than sold and 300x more Digital Credit issued than repurchased
00:18:47 - Returning $STRC to $99–$100 through USD reserves, Bitcoin monetization, repurchases, dividend management, and disciplined issuance
00:24:50 - Bitcoin liquidity: why Strategy’s bitcoin purchases and sales are not material to overall Bitcoin trading volume
00:33:03 - Bitcoin as Digital Capital: website metrics, the 200-week moving average, current headwinds, Bitcoin Dominance, banking adoption, and security coordination
00:44:08 - $STRC as flagship Digital Credit: liquidity, lower volatility, market depth, yield, investor base, path to par, and updated credit metrics
01:05:04 - Equity framework: hurdle rate, breakeven rate, floor rate, market skepticism, $MSTR outperformance, franchise advantages, and Strategy’s long-term ambition
Q&A
01:19:31 - Why Bitcoin-backed borrowing is not currently the preferred path to build USD reserves
01:23:11 - Why Strategy is consolidating around $STRC instead of creating more instruments or selling volatility
01:40:37 - Equitizing, repaying, or refinancing convertible debt
01:43:18 - Covered calls, cash-secured puts, Digital Credit, Bitcoin as money, and marketing products to the 99% outside Bitcoin
01:59:22 - USD reserve minimums and the path to $STRC trading at par
02:00:55 - Amplification, USD/BTC reserve mix, and countercyclical capital management
02:12:04 - Why Strategy does not intend to issue $STRC below par
02:20:34 - Lessons from 2022 and 2026, tokenized securities, Digital Money, and the June 26 dislocation
02:34:54 - Closing remarks
显示更多
Full Name: Sweetie Fox
Date of Birth: June 25, 2001
Age: 25 years (as of 2026)
Birthplace: Yekaterinburg, Russia 🇷🇺
Nationality: Russian
Profession: Actress, Cosplayer, Model & Social Media Personality
Marital Status: Unmarried
Physical Appearance
• Height: Approx. 5'5" (165 cm)
• Weight: Around 50–54 kg
• Eye Color: Blue
• Hair Color: Blonde
Net Worth & Impact
• Net Worth: Estimated $1 Million – $3 Million+
• Sweetie Fox has gained international recognition through her cosplay, modeling, and engaging online content. With a rapidly growing global fanbase and an active presence across multiple digital platforms, she continues to expand her influence while establishing herself as a popular content creator and social media personality. ✨
显示更多