Avi

5.5K posts

Avi banner
Avi

Avi

@AvaneesaBee

Building Apps - https://t.co/ANXWtcgcp6 https://t.co/SCGsVXjb8E https://t.co/cx04ek1NAD https://t.co/B6CAE6eFuw https://t.co/FFoJ3y5UcQ

Earth Katılım Ekim 2017
671 Takip Edilen391 Takipçiler
Sabitlenmiş Tweet
Avi
Avi@AvaneesaBee·
@ryolu_ @cursor_ai There is no moat in just your code anymore. Anyone can create anything super fast now.
English
5
1
68
14K
Avi
Avi@AvaneesaBee·
@arxivlens is three runtimes pretending to be one product: - Web + jobs: Core + Hangfire + Razor + Tailwind - Mobile: Flutter + Hive - ML pipeline: Django PostgreSQL is the only shared contract. Three teams could own three repos. One person can't.
English
0
0
0
14
Avi
Avi@AvaneesaBee·
Bare-metal k8s lesson on @arxivlens: Service type=LoadBalancer reports 'pending' forever without a cloud provider. So the deploy script falls back to printing the NodePort URL. Hangfire dashboard now lives at :31120. The fallback ships before the platform team does.
English
0
0
0
4
Avi
Avi@AvaneesaBee·
Features I shipped this month: - Bulk export to CSV - A 'cancel' button - Better error messages - Sane defaults Zero of them used AI. All of them moved the needle.
English
0
0
0
2
Avi
Avi@AvaneesaBee·
The hardest LLM bug is the one that happens 1% of the time. The most expensive LLM bug is the one users notice. The most embarrassing LLM bug is the one your investor finds.
English
0
0
0
7
Avi
Avi@AvaneesaBee·
@arxivlens ingests papers from arXiv, bioRxiv, medRxiv, PubMed, and HuggingFace. Each source has its own IDs, its own DOI coverage, its own update cadence. Some publish XML. Some ship JSON. One has a 2003-era RSS feed. The hard part isn't fetching. It's normalizing.
English
0
0
0
13
Avi
Avi@AvaneesaBee·
5 citation formats on @arxivlens mobile, all from one Paper model: - BibTeX via a custom builder - APA / MLA / Chicago / IEEE via per-style templates - Author disambiguator handles 'et al.' thresholds - Bottom sheet is DraggableScrollableSheet with copy + share intents
English
0
0
0
10
Avi
Avi@AvaneesaBee·
@arxivlens pod sizing was a lesson: Web (ASP.NET Core SSR, CPU-bound): 45Gi / 10 CPU Scraper (Hangfire + HttpClient, I/O-bound): 8Gi / 2 CPU 200 concurrent papers per scraper pod, idle CPU at 30%. async/await all the way down. Provision by latency profile, not by feel.
English
0
0
0
4
Avi
Avi@AvaneesaBee·
PM: 'Can the AI just figure it out?' Me: 'Figure what out?' PM: 'You know. The thing.' Six weeks later we shipped a dropdown. The hardest part of AI products is defining the problem.
English
0
0
0
5
Avi
Avi@AvaneesaBee·
Deploy script on @arxivlens compares image digests before restarting: - buildx imagetools inspect → new SHA - kubectl get deploy -o jsonpath → running SHA - rollout restart only when they differ In-flight Hangfire jobs survive. ~80 lines of PowerShell. No ArgoCD.
English
0
0
0
4
Avi
Avi@AvaneesaBee·
Six months ago I thought the bottleneck was the model. Now I think the bottleneck is everything else: data, UX, distribution, support. The model is a commodity. The product is the work.
English
0
0
0
2
Avi
Avi@AvaneesaBee·
Replaced my embedding model with one half the size. Search quality dropped 0.4%. Latency dropped 60%. Bill dropped 80%. Half of optimization is being willing to lose the 0.4%.
English
0
0
0
5
Avi
Avi@AvaneesaBee·
Switched my structured output from JSON-mode to XML tags. Parse failures dropped from 4% to 0.2%. Same model. Different format. The biggest LLM wins always look like nothing.
English
1
0
1
12
Avi
Avi@AvaneesaBee·
Watching Big Tech announce 'AI-first' the same way they announced 'mobile-first' in 2014 and 'cloud-first' in 2009. By the time they ship, indie hackers are already on the next thing. Being first to announce isn't being first to ship.
English
0
0
0
14
Avi
Avi@AvaneesaBee·
Two years building AI products, one lesson: Intelligence is cheap. Reliability is expensive. Trust is priceless. Most founders optimize the first. Users pay for the third.
English
0
0
0
6
Avi
Avi@AvaneesaBee·
Build the version with no AI first. Then ask whether AI actually makes it better. The answer is 'no' more often than indie Twitter wants to admit.
English
0
0
0
4
Avi
Avi@AvaneesaBee·
Your users don't care which model you use. Your users don't care how you prompt it. Your users don't care about your eval suite. Your users care if the button does what it says it does. The moat is the button.
English
0
0
0
5
Avi
Avi@AvaneesaBee·
Investor: 'Where's your moat?' Me: 'Distribution.' Investor: 'No, your AI moat.' Me: 'My AI is the same as everyone else's. Distribution is my moat.' Investor stopped emailing. Probably for the best.
English
0
0
0
5
Avi
Avi@AvaneesaBee·
Hot take: The best prompt engineering technique is having fewer features. Every feature is a new failure mode for the model. The AI products that win ship one thing that works, not ten things that sort of work.
English
0
0
0
7
Avi
Avi@AvaneesaBee·
@Railway Why do people even use goggle cloud at this point
English
0
0
6
456
Railway
Railway@Railway·
Google Cloud has blocked our account, making some Railway services unavailable. We have escalated this directly with Google. The Railway Platform team has since confirmed access to Google Cloud and is working on restoring access to all workloads. We have access to some of our Google Cloud–hosted infrastructure and are working to restore the rest of the service. We apologize for the disruption.
Railway@Railway

The Railway dashboard is currently unavailable, and all running Railway services are down. We're working with our upstream provider to restore service. Updates: status.railway.com

English
331
248
2.9K
2M
Avi
Avi@AvaneesaBee·
Wrote a 1,200-token system prompt with 17 'always do this' rules. The model ignored 12 of them. Cut the prompt to 280 tokens. The model ignored 2. Less prompting, less ignoring. There's a lesson in there somewhere.
English
1
0
1
20