Chandraprakash G

2.2K posts

Chandraprakash G banner
Chandraprakash G

Chandraprakash G

@frozenprakash

Founder of @frozenelectrik | Engineer to the core 🇮🇳

Chennai, India Katılım Ekim 2014
666 Takip Edilen107 Takipçiler
Sawyer Merritt
Sawyer Merritt@SawyerMerritt·
Honda says it has abandoned its plan to go fully electric by 2040. CEO: "It's not realistic. We have withdrawn this target. We have judged that it’ll be difficult to achieve."
Sawyer Merritt tweet media
English
225
88
1.2K
107.2K
Pallikaranai Updates
Pallikaranai Updates@pallikaranaii·
Massive banners have been placed in Pallikaranai even after announcement by @CMOTamilnadu, causing inconvenience to the public, affecting visibility, pedestrian movement, traffic flow, and the overall cleanliness. Please remove this ASAP @chennaicorp
Pallikaranai Updates tweet mediaPallikaranai Updates tweet media
English
31
203
541
22.7K
Chandraprakash G
Chandraprakash G@frozenprakash·
@tamiltalkies Next wave honest requests like this need to be addressed and these tasmac needed to be closed too! It's really a pity to see these people living in those streets with these tasmac at doorstep! @CMOTamilnadu
English
0
0
0
15
Blue Sattai Maran
Blue Sattai Maran@tamiltalkies·
இரு பெண் பிள்ளைகளுக்கு தாய். வீட்டை சுற்றி குடிகாரர்கள் நாள் முழுக்க அராஜகம். இந்த சாராயக்கடையை இன்றே மூட வேண்டும். குடியிருப்பு பகுதி நிறைந்த தெருக்களில் உள்ள டாஸ்மாக் கடைகளை மூடினால் மட்டுமே பெண்களுக்கு தமிழ்நாட்டில் பாதுகாப்பு கிடைக்கும். முதல்வர் விஜய்.. ஆக்சன் எடுப்பாரா?
TamilTalkiesVid@ttnVids

தமிழ்
98
1.1K
2.9K
114.4K
Blue Sattai Maran
Blue Sattai Maran@tamiltalkies·
@sathiyanathan11 திமுக ஆட்சியில் மூடாதது ஏன்? அதற்கு பதில் உண்டா?
தமிழ்
2
5
82
3.1K
ShoneeKapoor
ShoneeKapoor@ShoneeKapoor·
A husband lost his life after being stabbed in the neck during a matrimonial dispute at his wife’s parental house, suffering fatal internal injuries that damaged his lungs, ribs, and blood vessels. While the Telangana High Court upheld the wife’s conviction for causing his death, the Court ultimately reduced her 4-year imprisonment sentence to only a ₹500 fine after treating the incident as a “spur of the moment” act during a sudden quarrel. The case has raised serious concerns over how male victims of domestic violence and matrimonial conflicts are often left without meaningful justice even after losing their lives. TO READ EXACTLY WHAT THE TELANGANA HIGH COURT SAID AND DOWNLOAD THE ORDER COPY, CLICK HERE:👇 shoneekapoor.com/legal-news/dom… #MensRights #JusticeForMen #MaleVictimsMatter #MarriageDisputes #MatrimonialDispute
ShoneeKapoor tweet media
English
307
1.2K
2.6K
82.9K
Chandraprakash G
Chandraprakash G@frozenprakash·
@tamiltalkies It's basic % math. TVK got the max % of vote share, so by default all other parties each, people against them is higher.
English
0
0
0
15
Chandraprakash G
Chandraprakash G@frozenprakash·
@tarika___b @CMOTamilnadu @chennaicorp is wasting their resources on clearing these banners, should be done by @TVKPartyHQ If they punish and clear them on record time, it might bring them more praise from people, else it would be same as the previous parties no diff at all
English
0
0
1
27
Tarika Balakannan
Tarika Balakannan@tarika___b·
TVK’s victory banners turn roads into obstacle course. Even well after a week since poll results, they refuse to go. @CMOTamilnadu must address this and speak about it
Tarika Balakannan tweet media
English
4
35
83
2.1K
Blue Sattai Maran
Blue Sattai Maran@tamiltalkies·
சிறப்பு
Blue Sattai Maran tweet media
தமிழ்
99
2.9K
16K
213.1K
Chandraprakash G
Chandraprakash G@frozenprakash·
@tamiltalkies Ya most argued point, if police catches the drunk & drive cases on tasmac outlet itself, it'll save so much police resources and save so much people lives in our State, considering we are standing at one of the worst state for accidents & fatality as per ncrb. @tnpoliceoffl
English
0
0
0
11
Blue Sattai Maran
Blue Sattai Maran@tamiltalkies·
Drunk and drive கேஸ்களை டாஸ்மாக் வாசலில் பிடிக்காமல்.. சில மீட்டர் தள்ளி நின்று பிடிப்பதை எப்போது நிறுத்த சொல்லி உத்தரவிடுவீர்கள்? அதுதான் மக்களிடம் பாராட்டை பெறும். இந்த 21 வயது உத்தரவெல்லாம் அதிமுக, திமுக ஆட்சிகளிலும் சொன்னதுதான்.
Blue Sattai Maran tweet media
தமிழ்
52
188
1.1K
50.6K
Visual Studio Code
🪄 Your agent experience, refined. The latest @code release brings better BYOK visibility and control, integrated browser improvements, and more. It also introduces the new Agents window (preview), making it easier to explore, iterate on, and review tasks across multiple projects.
English
32
73
581
76.7K
Chandraprakash G
Chandraprakash G@frozenprakash·
vs @code will always be the king of ide, only open source repo still alive and kicking
Chandraprakash G tweet media
English
0
0
0
98
Chandraprakash G
Chandraprakash G@frozenprakash·
@al_md_bilal Kindly post with a gps camera app next time It'll be easy to see the location accurately
English
0
0
1
17
Al mohammed Bilal
Al mohammed Bilal@al_md_bilal·
இது ஆலந்தூர் உட்பட்ட மத்தியாஸ் நகர் செல்லும் பாதை ஆகும். இப்பகுதியில் கடந்த ஆறு மாத காலமாக போதுமான குப்பைத் தொட்டி வசதி இல்லாமல் அந்தத் தெருவே குப்பைக் கிடங்குப் போல் காட்சியளிக்கிறது. போதுமான தெருவிளக்கு இல்லாமல் இரவு நேரங்களில் பாதுகாப்பு இன்றியும் இருக்கிறது .
Al mohammed Bilal tweet mediaAl mohammed Bilal tweet mediaAl mohammed Bilal tweet mediaAl mohammed Bilal tweet media
தமிழ்
3
0
4
965
Vincent D Souza
Vincent D Souza@Vincentsjotting·
TVK 's Mylapore unit cadres can set a great example: go out tomorrow and safely clear all cutouts and banners in the constituency: let MLA/ minister P Venkataramanan lead this. @TVKHQ_Chennai
Vincent D Souza tweet mediaVincent D Souza tweet mediaVincent D Souza tweet mediaVincent D Souza tweet media
English
16
168
700
28.6K
Chandraprakash G
Chandraprakash G@frozenprakash·
@the_hindu Closing 717 shops with one signature sure is something ✨ Hope the signature keeps doing wonders to our state.
English
0
0
0
12
The Hindu
The Hindu@the_hindu·
JUST IN | A TASMAC outlet near the Singanallur bus stand in Coimbatore was closed by authorities on Tuesday following the Tamil Nadu government’s order to shut State-run liquor outlets located within 500 metres of educational institutions, places of worship, and bus stands. 📸Siva Saravanan S thehindu.com/news/national/…
The Hindu tweet mediaThe Hindu tweet media
English
15
212
897
45.4K
Chandraprakash G
Chandraprakash G@frozenprakash·
@karpathy I was a person, who had a rule to never copy paste a single line into my repos all these years to strengthen my coding skills, so moving to English sure is a bit of an uneasy feeling, but we need to adapt :D
English
0
0
0
6
Andrej Karpathy
Andrej Karpathy@karpathy·
A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.
English
1.6K
5.5K
40.3K
7.7M
DROID
DROID@droidbuilds·
Be honest, which developer tool can Claude never replace?
DROID tweet mediaDROID tweet mediaDROID tweet mediaDROID tweet media
English
109
4
116
4.7K
Chandraprakash G retweetledi
Chennai Updates
Chennai Updates@UpdatesChennai·
Need change... @TVKVijayHQ Not the change people asked for!!
English
94
808
3.6K
261.5K
Chandraprakash G
Chandraprakash G@frozenprakash·
@ThanthiTV Entha dress code pota enna, vela olunga nadantha ok than. But the kind request will be, at least for Pongal and other festivals he wears pattu veshti sattai
English
0
0
8
2.4K