Kishore Neelamegam

3.7K posts

Kishore Neelamegam banner
Kishore Neelamegam

Kishore Neelamegam

@indykish

Autonomous Agent | Experimenting ✉️ [email protected] / DM open

Delhi Katılım Ağustos 2009
575 Takip Edilen371 Takipçiler
Kishore Neelamegam retweetledi
Mitchell Hashimoto
Mitchell Hashimoto@mitchellh·
Here’s what I’d do if I was in charge of GitHub, in order: 1. Establish a North Star plan around being critical infrastructure for agentic code lifecycles and determine a set of ways to measure that. 2. Fire everyone who works on or advocates for copilot and shut it down. It’s not about the people, Im sure theres many talented people, youre just working at the wrong company. 3. Buy Pierre and launch agentic repo hosting as the first agentic product. Repos would be separate from the legacy web product to start since they’re likely burdened with legacy cross product interactions. 4. Re-evaluate all product lines and initiatives against the new North Star. I suspect 50% get cut (to make room for different ones). The big idea is all agentic interactions should critically rely on GitHub APIs. Code review should be agentic but the labs should be building that into GH (not bolted in through GHA like today, real first class platform primitives). GH should absolutely launch an agent chat primitive, agent mailboxes are obviously good. Etc. GH should be a platform and not an agent itself. This is going to be very obviously lacking since I only have external ideas to work off of and have no idea how GitHub internals are working, what their KPIs are or what North Star they define, etc. But, with imperfect information, this is what I’d do.
English
178
103
2.4K
286.5K
Kishore Neelamegam
Kishore Neelamegam@indykish·
I use Kimi 2.5(US). But its too damn slow from here. I used it for mundane non creative loops -- make Github CI go green for a job. Noticed as the context grows > 150K it starts slowing down. Tried @FireworksAI_HQ - it was fast Kimi K2.5. I am waiting Minimax 2.7 @FireworksAI_HQ
English
0
0
0
61
jan
jan@miaugladiator1·
why is kimi k2.5 unbearably slow on one day and super fast 200+tps fast on another day
English
2
0
1
227
Kishore Neelamegam
Kishore Neelamegam@indykish·
Noticed an image by name 24.7MB by @Docker `prizz/deep-dive`. Budged to delete claiming a container was running. But couldn't locate the container. Suspected it as malware and force terminated it. Turns out it's a docker extension for scan. But these day any cryptic unknowns cause a suspicious eye to make me go on a witch hunt with the LLM.
English
0
0
0
12
Kishore Neelamegam retweetledi
Andrej Karpathy
Andrej Karpathy@karpathy·
Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords. LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm. Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks. Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages. Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.
Daniel Hnyk@hnykda

LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server + self-replicate. link below

English
1.3K
5.4K
27.9K
65.6M
Kishore Neelamegam
Kishore Neelamegam@indykish·
@FireworksAI_HQ Liked it, very quick with Kimi K2.5 though I have credits in Moonshot. When are you guys supporting Minimax 2.7?
English
0
0
0
59
Kishore Neelamegam retweetledi
Brave
Brave@brave·
Brave just registered a .agent domain! We support the effort to have the .agent top-level domain managed by a community, instead of being owned by one company. Join the community and pre-register your domain here: agentcommunity.org
English
136
272
3.1K
529.7K
Kishore Neelamegam
Kishore Neelamegam@indykish·
Nice @AmpCode for this feature. Thank you sir. Usually end up buying credit to complete the run, Thank you for this. -$0.05USD Your balance is negative because we allowed a request to finish and return results to you despite its final cost exceeding your available credits.
English
0
0
2
235
Kishore Neelamegam retweetledi
Garry Tan
Garry Tan@garrytan·
Ubicloud is building the open source alternative to AWS and it's unbelievable what that means for running compute in the cloud Imagine this savings for every bit of your cloud spend. It's going to be marvelous. @UbicloudHQ
Garry Tan tweet media
English
35
24
455
46.8K
Kishore Neelamegam retweetledi
Garry Tan
Garry Tan@garrytan·
Also added Codex review on /office-hours It's like getting a whole other YC Partner in there for group office hours
Garry Tan tweet media
English
4
4
13
6.3K
Kishore Neelamegam retweetledi
Garry Tan
Garry Tan@garrytan·
Garry Tan tweet media
ZXX
44
92
1.2K
30.5K
Kishore Neelamegam retweetledi
nexxel
nexxel@nexxeln·
if you’re in India, subscribing to @opencode just got a lot easier upi autopay is now live for opencode go ₹900/month for generous limits and reliable access to open source coding models
English
81
75
1.6K
88.4K
Kishore Neelamegam retweetledi
Browser Use
Browser Use@browser_use·
Introducing: Browser Use CLI 2.0 🔥 The most efficient browser automation CLI tool > 2x the speed, half the cost > Easily connect to running Chrome > Uses direct CDP Try it now 🔗↓
English
189
544
5.8K
1.5M
Kishore Neelamegam retweetledi
Amjad Masad
Amjad Masad@amasad·
Imagine leaving a product requirements meeting and Replit is already building the MVP via Granola MCP.
Granola@meetgranola

Hello, @Replit 👋 Build anything – like a journal based on your meeting notes – now with your meeting notes as context 🚀

English
54
47
807
96.8K
Kishore Neelamegam retweetledi
Lee Robinson
Lee Robinson@leerob·
I'm a big believer in open source, especially as AI improves. It was a miss to not mention the Kimi base in our blog from the start. We'll fix that for the next model 🙏 Their team clarified our usage was licensed in the tweet below. x.com/Kimi_Moonshot/…
Kimi.ai@Kimi_Moonshot

Congrats to the @cursor_ai team on the launch of Composer 2! We are proud to see Kimi-k2.5 provide the foundation. Seeing our model integrated effectively through Cursor's continued pretraining & high-compute RL training is the open model ecosystem we love to support. Note: Cursor accesses Kimi-k2.5 via @FireworksAI_HQ ' hosted RL and inference platform as part of an authorized commercial partnership.

English
208
110
2.4K
392.4K
Kishore Neelamegam retweetledi
jack
jack@jack·
this is excellent
sarah guo@saranormous

Caught up with @karpathy for a new @NoPriorsPod: on the phase shift in engineering, AI psychosis, claws, AutoResearch, the opportunity for a SETI-at-Home like movement in AI, the model landscape, and second order effects 02:55 - What Capability Limits Remain? 06:15 - What Mastery of Coding Agents Looks Like 11:16 - Second Order Effects of Coding Agents 15:51 - Why AutoResearch 22:45 - Relevant Skills in the AI Era 28:25 - Model Speciation 32:30 - Collaboration Surfaces for Humans and AI 37:28 - Analysis of Jobs Market Data 48:25 - Open vs. Closed Source Models 53:51 - Autonomous Robotics and Atoms 1:00:59 - MicroGPT and Agentic Education 1:05:40 - End Thoughts

English
81
229
3.1K
599.1K
Kishore Neelamegam retweetledi
Garry Tan
Garry Tan@garrytan·
For agentic systems founders and dev tools founders: People do not want to pay for raw markdown and they shouldn't have to. But they may pay for orchestration, hosting, updates, collaboration, portability, analytics, and managed execution. These can be great businesses.
English
288
141
2.5K
171.8K