Hacker News: se4u

Show HN: Beating GPT5.5-xhigh for Coding agent security with SLMs and IRM

se4u — Thu, 27 Aug 2026 22:33:19 +0000

Coding agents craft arbitrary code so securing them is more complicated than red-teaming. We post trained a cyber-security small llm, changed how it reasons and supplemented our controls using program analysis techniques such as inline reference monitoring to outperform GPT5.5-xhigh on hard benchmarks like LinuxArena and SleightBench.

Free product available at harden.run and full benchmarks in the blog post.

Comments URL: https://news.ycombinator.com/item?id=49472151

Points: 9

# Comments: 5

New comment by se4u in "Kimi-K3 Technical Report [pdf]"

se4u — Mon, 27 Jul 2026 18:26:40 +0000

Your best bet will be to start a network optimized ec2 (or gcp compute instance) and save to some bucket. Cloud network will be a lot more stable than home.

New comment by se4u in "Claude Fable produced a counterexample to the Jacobian Conjecture"

se4u — Mon, 20 Jul 2026 05:52:33 +0000

You can't please everyone on the internet, if he had posted this on Arxiv then someone else will be complaining that Arxiv is for humans to publish and that llm output should be social media post instead. Also, the proof fits in a tweet. So why blow it up.

New comment by se4u in "Show HN: I RL-trained an agent that trains models with RL (for ~$1.3k)"

se4u — Tue, 14 Jul 2026 20:50:01 +0000

that's because they said they'll silently fallback in case of model training. Then they backtracked, and said they wont silently fallback, but how will anyone ever know?

New comment by se4u in "Computer-Aided Language Development in Nonspeaking Children (1968) [pdf]"

se4u — Tue, 30 Jun 2026 17:32:03 +0000

My daughter suffers from Autism Level 3 and I worked with my daughter's speech therapist and OT to build tejutalks.com which helps nonverbal children communicate with the help of AI.

It's being used by around 10 kids for the last 3 months and it's really helped some of them to demonstrate that they know a lot more than they can say.

It uses Openai models underneath, although initially I started with local inference using MLX. If anyone is curious feel free to reach out.

New comment by se4u in "Formal Verification Gates for AI Coding Loops"

se4u — Thu, 21 May 2026 02:03:52 +0000

Hi, thanks for the writeup, I wonder for the auth problem what you think about rego and OPA type solutions and their place in world in comparison to generated guards?

New comment by se4u in "An OpenAI model has disproved a central conjecture in discrete geometry"

se4u — Wed, 20 May 2026 23:53:51 +0000

When a qualifying noun is absent , then priors means prior beliefs.

New comment by se4u in "How to Build the Future: Demis Hassabis [video]"

se4u — Thu, 30 Apr 2026 00:38:56 +0000

You do realize that djmips is Demis' account?

New comment by se4u in "Google plans to invest up to $40B in Anthropic"

se4u — Fri, 24 Apr 2026 22:02:04 +0000

I'd be interested to learn what kind of internal tooling are you improving ?

New comment by se4u in "Israel escalates attacks on medics in Lebanon with deadly 'quadruple tap'"

se4u — Fri, 17 Apr 2026 22:20:38 +0000

> ... the person next to him is probably also a combatant

Absolutely, they could even be future combatants even if they are not now. That's why killing schoolgirls in Iran, reporters in Lebanon, etc. is justified, they are all potential terrorists. It definitely can not be proven otherwise that they are not. Why take a chance? /s

Ask HN: How do you distinguish prompt issues from model failures in LLMs today

se4u — Wed, 18 Mar 2026 16:39:24 +0000

Comments URL: https://news.ycombinator.com/item?id=47427959

Points: 2

# Comments: 0

New comment by se4u in "Ask HN: What Are You Working On? (March 2026)"

se4u — Wed, 18 Mar 2026 16:33:48 +0000

Building VizPy, a prompt optimizer we've been working on for a while now.

The problem it's solving is one most people building with LLMs know well. Your prompt fails on some inputs, you don't really know why, and you end up just tweaking and re-running until something sticks. We kept hitting this ourselves and it felt like there had to be a better way than guessing.

What we figured out after a lot of research: prompt failures almost always follow a pattern. The model isn't failing randomly, it's consistently failing on a particular type of input or reasoning step. VizPy finds that pattern, distills it into a plain English rule you can actually read, and then rewrites your prompt around it. You also get the rule itself so you can review it, tweak it, or just drop it into your existing prompt directly. DSPy-compatible, no pipeline rewrite needed.

We have compared it extensively against baselines such as GEPA on benchmarks like BBH, HotPotQA, GPQA Diamond, and GDPR-Bench and VizPy wins on all of them. We'll have more benchmarks on cyber-security and chip-design coming out soon.

Free to try, 10 runs no card: https://vizpy.vizops.ai/

New comment by se4u in "We recreated the Anthropic C compiler agent"

se4u — Tue, 10 Feb 2026 17:15:33 +0000

Anthropic released a C compiler this week that was built autonomously. We mined the entire repo for clues to reproduce the scaffolding they used and open sourced it.

We recreated the Anthropic C compiler agent

se4u — Tue, 10 Feb 2026 17:15:33 +0000

Article URL: https://vizops.ai/blog/agent-scaling-laws/

Comments URL: https://news.ycombinator.com/item?id=46963189

Points: 1

# Comments: 1

New comment by se4u in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"

se4u — Fri, 11 Jul 2025 23:15:09 +0000

FYI, It wasn't taken the money and leave, a lot of them got absorbed into GDM.

Source: I was in GDM when character was acquired.

New comment by se4u in "The year I didn't survive"

se4u — Wed, 12 Feb 2025 22:27:35 +0000

+1 to this, my mom died because of COVID in India 1 months after she left US after visiting me, and I still feel guilty that I didnt insist on getting her the vaccine before she left for India, and then at the time of her death India was locked down so no flights and I wasn't even next to her. It's been 4 years but every so often I think about this. I blame myself less now after some therapy, but If you didn't try all that you could you'd probably feel guilty like me.

New comment by se4u in "Citations on the Anthropic API"

se4u — Fri, 24 Jan 2025 04:04:19 +0000

Yeah I don't understand why the whole thread has been so hostile against a very reasonable/useful observation that you made. If there was a way to prompt commenters to be less snarky on HN that'd be a vast improvement.

New comment by se4u in "Supreme Court upholds TikTok ban, but Trump might offer lifeline"

se4u — Fri, 24 Jan 2025 00:26:00 +0000

The brits were also running the opium shops. So if you think country A selling opiods in country B and then going to war so that country B can not stop the sale of opiods is totally okay, then that is truly very different from my model of good behavior.

New comment by se4u in "Supreme Court upholds TikTok ban, but Trump might offer lifeline"

se4u — Fri, 17 Jan 2025 16:39:10 +0000

Have you seen YouTube shorts and Instagram reels. Lol

New comment by se4u in "Supreme Court upholds TikTok ban, but Trump might offer lifeline"

se4u — Fri, 17 Jan 2025 16:37:43 +0000

I don't know if you are just ignorant about history and unwilling to Google, or if you are making the point that of course British did not force feed opium to the people.

What is very well established is that the british fought a war , literally called the opium war by Western historians themselves with the main objective of keeping their opium distribution into China open after the emperor banned it

Their action was akin to if some majority owner of Purdue pharma invades US and forces US government to "keep the oxy market open" while letting "people make their own decision".