Slava S. (@slvDev) header
Slava S. (@slvDev) profile picture

Engineer building everything in public Background: CGI | GameDev | Fullstack | ML | Web3 Goal: $2k MRR | Current: $150 MRR

Ukraine
Joined January 2015
Replying to @AnthropicAI
@AnthropicAI when Opus 5.6? we are want it already!
255
tested new Claudflare CLI that fully supports agents rly cool, whole claudflare in one prompt. prompt: "set up support@ email for my domain" - remove 6 old mail records - turn on email Routing (MX, SPF and DKIM added automatically) - create the rule and add DMARC - test email arrived a few minutes later
2
2
652
live dashboard showing how it works on the Uniswap V3 WETH/AAVE pool (2x speed)
finally added full @base history indexing to Sieve! no archive RPC needed anymore to get old events on Base. Sieve pulls history straight from Base public snapshot archives, then switches to P2P. - archive-plan: estimates which archives your block range needs + disk space - downloads them, verifies checksums, keeps only your events, deletes the raw files - catches up the gap from Base peers (each block confirmed by 3+ peers) - switches to follow mode and indexes new blocks live if you build on Base and need events, you don't have to pay for RPC!
2
5
327
finally added full @base history indexing to Sieve! no archive RPC needed anymore to get old events on Base. Sieve pulls history straight from Base public snapshot archives, then switches to P2P. - archive-plan: estimates which archives your block range needs + disk space - downloads them, verifies checksums, keeps only your events, deletes the raw files - catches up the gap from Base peers (each block confirmed by 3+ peers) - switches to follow mode and indexes new blocks live if you build on Base and need events, you don't have to pay for RPC!
1
1
1
11
790
check your chatGPT PRO subscription options $500 plan goes live
263
OpenAI drop new Pro 500 subscription
203
idk why people say that new opus5.5 has like an unlimited quota. normal use in ONE project (complex one), several instances, loops etc Thursday morning Max x5 plan will be drained...
1
195
whole AI community right now hehe
Replying to @claudeai
Sonnet 5.5 improves on Sonnet 5 across benchmarks, in some cases dramatically. It’s a faster, lower-cost complement to Claude Opus 5.5, strongest at well-scoped everyday tasks, fixing bugs, and creating polished documents, slides, and spreadsheets.
1
232
Replying to @IndependentEco
idk, max x5 on opus 5.5 and hit limit easily
4
25
4,267
opus 5.5 max, motion design, one prompt "create 15+ sec self-promotion promo"
lets test opus 5.5 medium (not max) in motion graphics from simple prompt thats rly impresive! finally $20 plan gives you more room for creativity
2
2
1
22
22,514
Replying to @TheSpacerr
im not sure about that
14
lets test opus 5.5 medium (not max) in motion graphics from simple prompt thats rly impresive! finally $20 plan gives you more room for creativity
2
1
5
1,792
soldered and tested first run in the car failed :) spent a while debugging... turned out i plugged the HAT into the wrong row of the sticks header, heh now it runs smooth, ~2k frames/s 0 dropped frames in 5 min driving will show how numbers behave on the road
previous setup was too complex esp32 + CAN + dc-dc, and the stickS3 read it over wifi so I designed a HAT for @M5Stack StickS3 it powers the stick from the car's 12V and converts CAN signals for the stick i believe it's way more handy than a separate dongle case is printed time to solder and test
4
13
231
33,328
everyone is training fruit flies to do some crazy stuff, but what if we don’t train one at all and put part of its connectome on an ESP32-S3... lets try here is what I was able to fit on it: - 48,311 neurons - 9.46M connections no training, and it runs fully on the chip spider approaches then escape neurons activate and the fly jumps it works! fly connectome with simplified neuron dynamics the bars on top show escape neuron activity for each side the simulated spiders distance and direction stimulate the fly’s looming-detector neurons. activity travels through the connections, then I read 8 escape neurons when one side crosses a threshold, it triggers a jump away from that side (not always perfect) I coded the world, sensory input and jump rules but the connectome produces the neural response and seeing it in action on this tiny board is sooo cool!
1
1
37
4,460