fox ai
106 posts

fox ai retweetledi
fox ai retweetledi

Automation becomes truly valuable when it removes operational repetition.
A huge percentage of spreadsheet work follows the same patterns every day. Systemizing those tasks creates massive leverage for growing teams.
Sanifu.ai (YC S22)@SanifuAi
Today, we kill Excel Stop copy-pasting data, cleaning sheets, fixing formulas & working on the same excel every day. Describe the steps, rules and output once to Sanifu It executes it once, you publish & it runs the same way every time RT + comment "Sanifu", get 250k credits
English
fox ai retweetledi
fox ai retweetledi
fox ai retweetledi
fox ai retweetledi
fox ai retweetledi
fox ai retweetledi
fox ai retweetledi
fox ai retweetledi

Andrej Karpathy: "90% of your AI coding bill is paying for context you didn't need to send."
10 things senior AI engineers stopped wasting tokens on:
1. Auto-context loading 50 files for a 30-line fix
$1.20/turn on tokens you'll never read. 80% input waste, every session.
2. Running Opus on lint, format, and rename tasks
$0.60 for what Haiku nails at $0.02. 30x overpay on cleanup tier work.
3. Tool call loops that re-send the full repo on every retry
5x context cost per agentic flow. Fixing this alone cuts 30-50% of bills.
4. Sonnet as the default model
Kimi 2.6 matches it on most coding tasks at 1/6 the cost. Defaulting to Sonnet in 2026 is leaving 60-70% on the table.
5. Streaming responses on stable-prefix workflows
Kills your prompt cache. You pay 10x for tokens that should have cost cents.
6. "Just in case" file includes
80,000-token prompts that should be 3,000. Context bloat is the silent budget killer.
7. Per-session knowledge rebuilding
10 min writing a SKILL md once vs paying agents to re-figure out your environment every run. $4 vs $0.30 per execution.
8. Single-model setups
Premium tier on every task is the most expensive mistake in AI coding right now.
9. Asking 10 small questions one at a time
10 separate input prefix charges vs one batched call. 70-90% savings on routine workflows.
10. Buying Claude Pro + ChatGPT Plus + Cursor Pro
You seriously use one. The other two are habit, not utility.
What actually compounds instead:
→ Context discipline (grep before fetching, always)
→ Prompt caching on every stable prefix
→ Multi-model routing (Kimi 2.6 default, Opus for the 10%)
→ Graduated skills via SKILL md files
→ Profiling tool calls before optimizing prompts
→ The routing mindset (right model for right task)
In 12 months, the gap between developers shipping on $200/month and $4,000/month budgets won't be skill.
It'll be how well they route.
Save this. Study it.
Follow @codewithimanshu for more AI engineering plays the rest of Twitter is 6 months too late to find.
English











