AI enthusiast + Open-source advocate + Cheese lover

San Francisco
Joined December 2023
ThorneSophia CodeCheese retweeted
Does vibe coding make prototypes easier or production software riskier?
40
3
43
1,366
ThorneSophia CodeCheese retweeted
Microsoft has priced its Nvidia RTX Spark PCs, with the Surface Laptop Ultra starting at $2,599 and the Surface RTX Spark Dev Box at $5,999. > Up to 128GB of unified memory > Runs AI models of up to 120 billion parameters locally, no cloud needed > Up to 1 petaflop of AI compute > Up to 20 CPU cores and 6,144 CUDA cores > Microsoft claims up to 2.1x faster time to first token, 4.3x faster AI image generation and 6.2x faster AI video generation than a 16-inch M5 Pro MacBook Pro > World's first laptop with a breakaway USB-C port > Base model gets 24GB, the 128GB laptop costs $5,899.99
6
10
4
189
24,719
ThorneSophia CodeCheese retweeted
Claude Haiku 5.5 mogs GPT-6 Luna across every single benchmark. Haiku scores more than 2x higher than Luna on Terminal-Bench 4.0! Up to 100k tokens, they are the same price. Past 100k tokens, Haiku costs 5x of Luna. Who is building the world's most specific router, that routes subagent tasks to Haiku under 100k tokens and Luna otherwise? Should I do it?
7
4
43
3,402
ThorneSophia CodeCheese retweeted
My timeline needs more people who are building things. If you're into software development ,writing, AI or building your own products, let's connect 🤝
15
3
30
664
ThorneSophia CodeCheese retweeted
A good Hermes skill saves you from explaining the same workflow every session. Cheat Sheet 03: find it, inspect it, install it, use it, keep it current. Read the instructions and scripts before you hand them the keys.
3
4
27
1,445
ThorneSophia CodeCheese retweeted
What if the jagged frontier is mainly math + code (which you can push arbitrarily far with RLVR), and everything else starts to plateau because it is still bottlenecked by human generated data? Model performance in non-verifiable areas has kept improving steadily, albeit much slower than for math and code. But is that steady improvement a side effect of a higher G (itself driven by RLVR), or only a function of the amount of new human data getting injected into training (which is still continually happening on a massive scale)? A lot of things depend on the answer to this question
208
177
59
2,209
232,605
ThorneSophia CodeCheese retweeted
Honestly stunned by result 128 Shortest Common Superstring went from 3x optimal to 7/3 over 35 years of human work. OpenAI's model got it to exactly 2. And it didn't use greedy, the algorithm the 1988 conjecture was about. Lean-checked I animated the proof in 6 minutes:
OpenAI
@OpenAI
Oct 6
We’re releasing a broad range of new mathematical results produced by an internal frontier model. We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results. github.com/openai/math
21
71
12
808
68,802
ThorneSophia CodeCheese retweeted
Can vibe coding produce production ready software without an experienced engineer?
103
3
6
94
8,758
ThorneSophia CodeCheese retweeted
Anthropic to adopt Samsung as foundry partner Always been bullish on Samsung and now you can see their foundry business making huge moves. Fast becoming a strong, big, viable 3rd foundry player. On another Samsung news, SOUTH KOREAN media reporting that SAMSUNG’S 12-HIGH HBM4E PASSES QUALIFICATION TESTS AT $NVDA and other customers Samsung 🚀🚀 $TSM $DRAM $INTC $EWY
3
6
41
2,242
ThorneSophia CodeCheese retweeted
What happens if the US (through the utilization of frontier models) develops a cure and starts price gouging the rest of the world, especially the drifters, something like $1k per person? Or maybe even higher? A cure to a disease, so simple as the Pneumonic Plague, is literally a few prompts away (plus a day of work of a few thousand agents) for the currently unreleased and gated models of OAI and ANT.
Benny Johnson
@bennyjohnson
Oct 5
This is the best analysis of the Pneumonic Plague on the internet. It looks like this strain may have been altered to resist treatment. That’s what a bioweapon looks like. Serious. Watch…
1
2
2
851
ThorneSophia CodeCheese retweeted
7 Linux commands that give you instant answers on a struggling server: 🐧 1. uptime: Check 1, 5, and 15-minute load averages against your total CPU core count. 2. vmstat 1: See CPU idle percentage, memory swapping, and IO wait blocks every second. 3. mpstat -P ALL 1: Check if one single CPU core is pinned at 100% while others sit idle. 4. iostat -xz 1: Measure disk read/write bandwidth and average request queue size. 5. free -m: Check actual available RAM without getting confused by OS buffers. 6. ss -s: Summary of total open TCP connections and time-wait sockets. 7. pidstat 1: Pinpoint the exact process consuming CPU, disk, or memory in real time. Save this cheat sheet for your next server investigation. 📌
3
3
8
670
ThorneSophia CodeCheese retweeted
quick heads up if you use Gemini for free starting Oct 9, you'll only get flash-lite, google's smallest model. flash and pro go away on the $4.99 ai plus plan, you keep flash but lose pro. ai pro and ultra keep all three your usage limits don't change. you just get fewer models to pick from
8
2
12
404
ThorneSophia CodeCheese retweeted
DHH
@dhh
Oct 6
I sympathize with programmers who worked on systems they never cared about, for customers they didn't connect with, and took all their working joy from the mechanical act of turning tickets into code. You have to care about the software to be excited about making it w/ agents!
162
258
57
4,521
203,266
ThorneSophia CodeCheese retweeted
$IONQ UPDATE: We hosted IONQ CFO/COO Inder Singh in investor meetings. Key takeaways include: 1) Superion 256 PQ system ramping in 2027E with ASP potentially in $25-30M, 2) IONQ continues to see upside from deployments in CSP clouds as it works on modular scalable platforms for its next-gen 10K PQ system, 3) upside with research labs/sovereigns as US pushes adoption of Post-Quantum Cryptography (PQC) standards in 2027E, with 2030-35E compliance targets, and 4) SKYT integration driving continued performance/roadmap acceleration, with own foundry, potentially set to reduce fab cycles from 8 to -2-3 months and potentially drive foundry revenue up ~100% y/y. Reiterate IONQ at Outperform with a $52PT, as we see its 256PQ Superion system driving 2027E upside, while vertical integration drives a scalable platform and also provides a flagship onshore industry QC foundry.
$IONQ | Mizuho Securities 𝗺𝗮𝗶𝗻𝘁𝗮𝗶𝗻𝘀 𝗕𝘂𝘆 on 𝗜𝗼𝗻𝗤, 𝗜𝗻𝗰., maintains PT at $𝟱𝟮
2
18
117
6,961
ThorneSophia CodeCheese retweeted
My main problem with Dots, is it's not sparks joy yet. ChatGPT sparks joy, Codex sparks joy, Dot is not yet.
1
38
ThorneSophia CodeCheese retweeted
Where does the time actually go when an AI agent runs? Total response time: 2,400ms. The breakdown: - User Network Roundtrip: 80ms - Query Embedding Generation: 60ms - Vector Database Hybrid Search (pgvector): 40ms - Prompt Assembly & Context Injection: 10ms - Time to First Token (TTFT) from LLM API: 650ms - Model Output Generation (300 tokens): 1,200ms - Pydantic Validation & Tool Execution: 360ms If your users complain about speed: Optimizing the database search saves 20ms. Streaming tokens with Server-Sent Events (SSE) saves 1,200ms of perceived wait time. Always stream your outputs. Are you streaming LLM tokens or waiting for the full response to finish?
4
4
1
16
831
ThorneSophia CodeCheese retweeted
i didn't wanna waste my time and yours on another article you'd bookmark and never use... master CHATGPT DOT in 4 screenshots. thank me later.
25
22
2
155
10,072
ThorneSophia CodeCheese retweeted
A few things to think about as AI gets more capable: 1. Intelligence is becoming abundant and limitations are moving somewhere else. Good judgment, good questions, good data and knowing what to do with an answer are becoming more valuable than simply having access to a model. 2. The cost of trying an idea has collapsed. You can build a prototype, analyze a market, test a workflow or write the first version of a product in an afternoon. That changes how I think about ideas. There is less reason to debate something for three months when you can test it this week. 3. Most of what gets produced with AI will be mediocre. That makes taste more valuable. When everyone can produce ten versions of something before lunch, knowing which one deserves to exist becomes a real advantage. 4. A lot of AI value will sit outside the model. Models will improve, prices will change and providers will come and go. The data, workflows, infrastructure and relationships built around those models can become much more durable assets. 5. Access and ownership are two very different things. Renting intelligence from a provider is incredibly useful. Having some control over the compute, data and systems your business depends on gives you a different kind of leverage. 6. AI is also changing the size of a company that can do meaningful things. A small team with access to good models, software agents and the right infrastructure can take on work that would previously have required a much larger organisation. 7. This is why I keep coming back to user-owned infrastructure. If AI becomes one of the basic layers of the economy, I don't think every person and business should have to remain a permanent tenant of someone else's infrastructure. There is a lot of excitement around what AI can do, we should be more interested in what kind of economy we build around it.
8
49
1
53
710
ThorneSophia CodeCheese retweeted
the way opus 5.5 spatially align text in images in iterations is so beautiful, openai's web harness is lacking in this capability of analyzing plots it just constructed w/ code. image_1: bad spatial text alignment, image_2: next self-corrected iteration of great text alignment.
1
1
8
726
ThorneSophia CodeCheese retweeted
Top 10 system design resources that actually help in day-to-day backend work + interviews: 1) Designing Data-Intensive Applications (Kleppmann, book) Replication, partitions, consistency, storage engines. Great for arguing tradeoffs. 2) Site Reliability Engineering (Google, book) SLIs/SLOs, error budgets, capacity planning. The ops side most designs ignore. 3) System Design Primer (GitHub) Free. Lots of common components (LB, cache, queue) with quick pros/cons. 4) AWS Well-Architected Framework docs Concrete checklists: reliability, cost, security, ops. Use it to review your own design docs. 5) Martin Fowler’s architecture articles (fowler.com) Strangler fig, event sourcing, CQRS, microservices failures. Good for naming patterns correctly. 6) High Scalability (highscalability.com) Real-ish architecture breakdowns. Helps with “what does a big version look like” intuition. 7) Designing Distributed Systems (Brendan Burns, book) Kubernetes-style patterns: leader election, work queues, sidecars. Practical distributed primitives. 8) MIT 6.824 Distributed Systems (course + labs) Harder, but it forces you to reason about failure modes, not diagrams. 9) Jepsen blog + Knossos writeups Learn what breaks under partitions and clock issues. Makes “exactly once” claims disappear fast. 10) Practice project: build a tiny production-ish service API + Postgres + Redis cache + queue worker + tracing + load test (k6). Add one failure drill: kill DB, throttle downstream, replay a poison message.
6
4
1
38
2,002